explorer

View the Project on GitHub gavagai-corp/explorer

Explorer Documentation

Gavagai Explorer is a tool to analyze related texts to find common topics, their associated terms, their sentiment scores and their prevalence in the data (number of respondent mentions). Although the primary use case for Explorer is the analysis of open-ended survey responses, it can be used to analyze any set of related texts such as product reviews, Net Promoter Score programs, or social media opinions for a given target-of-interest.

Gavagai Explorer aims to give the analyst a comprehensive and quantified view of the unstructured input data. It identifies the main topics or themes, measuring their importance as a relative strength to the total number of texts. This means that the strength of a topic is comparable across different data sets.

This documentation introduces the main features of the Gavagai Explorer and guides you through using these features effectively.

1 Introduction

All of Gavagai’s services are built on top of a core system called the Gavagai Living Lexicon, which continuously learns languages by ingesting newly published texts from the Internet. Through this process the lexicon learns about the vocabulary of the language and the relationships between words and multiword expressions. From this understanding we can extract useful information in our services. For more information about the Living Lexicon’s website.

In Gavagai Explorer, you can see the effects of the Living Lexicon working in the background by looking for suggestions of related terms in each topic. Each suggestion is taken from the knowledge we have of relationships between words. You can also look for multiword expressions (like ‘San Francisco’) which are built automatically from the system’s general knowledge of language.

2 Getting started with Explorer

Gavagai Explorer is a web-based application that is best experienced using Google Chrome. You can download Chrome here

2.1 Creating an account

You need to create an account with the Gavagai Explorer before you can start to analyze your texts. To get a free trial account, open this link in your browser: https://explorer.gavagai.se, click the ‘Try for free’ button and follow the instructions.

2.2 Creating a project

َTo start using the Explorer you need to first create a project. Add a new project by clicking on the ‘Create project’ button on the Explorer homepage.

When you press this button you will be redirected to a new page where you can give a name to your project and load your data. Write the name of your project in the text field. Note that you can edit the project name later in the project’s ‘Edit’ page. Load the data to be analyzed by clicking the ‘Choose file’ button and select a file in a csv format (comma separated values to represent data in columns) or an Excel file (either .xls or .xlsx).

When you choose your target file, you will be redirected to the Explorer homepage (‘My Projects’) where you can see the list of your projects including the one you just created. Wait a few seconds until Explorer completes pre-processing your data and your project status turns to ‘Ready’. Under the name of each project you can see it’s status, amount of texts and columns, size and the date it was created. It will help you navigate between all your projects. There’re also 2 buttons on the right which enable the user to delete a project or to go to its edit page directly.

Now you can click the Explore button to start analyzing your data. The first time that you click Explore for a new project, you need to do a basic configuration and click Explore once more before Explorer analyzes your data.

You can also arrange your projects in different folders for easier navigation. Add a new folder by clicking on the ‘Create Folder’ button on the Explorer homepage. You can then rename folders, drag-and-drop projects in and out, and delete them if they are no longer needed. Please remember that you can only delete empty folders.

2.2.1 Preparing an upload file

Both file types that are compatible with the Explorer (.xlsx and .csv) store data in columns and rows. For the Explorer to correctly process your file, the uploaded data should be laid out in a particular way.

Each line of the file should correspond to one verbatim. According to your use-case, this could be a document, a product review or a tweet. All texts for analysis should be located in the same column of your file, as the explore process is carried out on a single column. We will refer to this as the ‘main text column’. In other columns of the sheet, you can optionally include metadata about the text (e.g. date, location, author_id), which can later be used for reference or for filtering your data inside the Explorer.

The file should also begin with a header row, containing appropriate titles for each column.

Here you can find an example file containing hotel reviews that is laid out in the correct way. There are four columns containing metadata, plus a main text column which is entitled ‘review’.

In .xlsx files, it is possible to leverage formulas for processing data, for example: to concatenate text or to calculate time intervals. This is completely compatible with the Explorer for both metadata and textual data. In pre-processing, the system knows to take the resulting value of the formula, rather than the text of the formula itself.

2.2.2 Appending additional data

It’s also possible to add several files to an existing project by uploading another CSV (.csv) or Excel file (.xlsx, .xls). Please note that additional files must have exactly the same columns. To add more data, go to the project Edit page and scroll to Add More Texts section. Drag and drop the new file or choose one from your computer.

The project’s status will change to Appending and when it switches back to Ready you can start/continue working on analysis. You must re-explore the project to have the new data taken into account. The amount of rows in the project should change according to the appended file, but if there are pinned topics and/or groups in the project - they should all remain in place. See section 3.1.2.1 Pin Button You can see the history of uploads to every project: date added, file name, format and the amount of rows.

2.2.3 Deleting data from a project

As mentioned in the section above, it’s possible to add more data to an existing project. In the same way, you can delete data that was appended. On the project Edit page, scroll down to history of all appended files. Choose the one you would like to delete and click on the trash bin symbol. The confirmation pop-up will appear and after clicking Yes, delete the project status will change to Deleting.

During the Deleting status the append history will be grayed and it’s not possible to make any more changes until the deleting is complete. It can take some time depending on the file size and you can reload the page to see if the status has changed. After deleting the amount of rows in the project should change accordingly.

2.3 Basic Configuration

You first need to specify the main text column that you want to explore. Explorer automatically detects the biggest column in the uploaded file and chooses it as a column for analysis. If you’d like to have another column instead, just choose it in the drop-down menu. To make it even more easier to choose the right column, a preview of the 3 first rows is shown. Note that if your file consists of more than one text column, and you would like to explore more than one of them, you need to create a separate project for each of these columns. You also need to choose the language of your texts. When you select the text column, Explorer flags the language automatically. After you select the main text column and the language, there are the following optional configurations that you can apply to your project.

When you are done with basic configuration, you can either click on Explore to start analyzing your data or set up more advanced configurations for your project.

2.3.1 Applying a Template Model (Optional)

You can apply a model as a template to your project. In chapter 8 we explain how models are created and used in Gavagai Explorer.  

2.3.2 Filter Conditions by MetaData (Optional)

You may optionally set up some filtering conditions on values from other columns than your main text column. In the drop-down menu you will find those columns that are candidates for filtering - this means those columns that have a few different values repeated over and over, like ratings, or gender. Then you can choose which values are accepted for that column. After choosing the accepted values, save your settings by clicking on the ‘Add filter’ button.

You might apply filtering conditions to divide your data into smaller groups and analyze each group in Explorer independently; e.g. for employee’ reviews of a large company you might divide your data to company’s departments, or you might divide it into two group of males and females. You might also filter texts based on the level of respondents’ satisfaction by selecting specific values of ranks or ratings.

Another application of filtering columns is where you have very large amount of data which cannot be analyzed by Explorer at once. In this case, you may, for instance, filter data based on time periods (e.g. monthly basis).

2.3.3 Filter Conditions by Date Range (Optional)

It’s also possible to specify the date format and select a particular date range for filtering. In the Date range filter drop-down menu choose the column that contains dates and you will see samples, it should help you choose the right column. You can also change the date format in the field below and test it - the dates should match the samples.

Then you can choose the date range of the texts you would like to filter out. Just set from/to dates and click on Add filter.

When the filters are applied, Explorer button will show that you are working with the filtered results. To go back to the complete dataset, you need to remove the filters and click on Explore again.

When you are done with basic configuration, you can click on Explore to start analyzing your data.

2.3.4 Concept Filtering

You can filter the contents of the project based on concepts that you have in your account. For more information about creating and using concepts see section 7. Concepts can be used to qualify the texts that are part of your current analysis - texts will be included in the analysis if they match the configuration of the concept filter. This can be done when producing a report (as described in section 9.2.3), and it can be done when exploring a project interactively.

A concept filter works by looking for its terms in the texts of the project, and depending on the settings described below, matching texts will be included or excluded in the analysis. Texts are matched on any terms in the concept and for a match to be valid it must be exact.

The concept filter configuration can be done at any time while working with a project and you can find the control for the configuration in the main configuration screen for the project.

In the drop-down menu you will find all concepts available in your account. If you select a concept from the menu a filter entry will appear below the menu:

The concept name is followed by its ID and two options:

To apply the concept filter you need to update and save the project by clicking the ‘Update and save’ button. If you remove the concept filter by clicking the small x at the right all texts will be included as usual in the next update of the project.

When the concept filters are applied, Explorer button will show that you are working with the filtered results. To go back to the complete dataset, you need to remove the concept filters and click on Explore again.

2.3.5 Include MetaData (Optional)

If metadata exists in a given project, you can choose to add up to 3 metadata columns from a drop down menu. The information from the columns you specify will be added to the text examples of the topics - for better understanding and analysis. You can change the columns and see the result directly - no re-exploration is needed.

2.3.6 Generate Stories (Optional)

Stories give you another way to look at your analyzed data and let you organize your data independently of the exploration results. It shows the main topics using the clustering algorithm which has been optimized for analyzing editorial and media content like newspaper articles. It will find the common events and topics across all texts and also present the stories graphically in an easy-to-understand manner. Please note if you want to generate a report (such as the Excel report) there is a maximum of 2000 reviews for your project. To turn on Stories your project must contain two meta-data columns:

You also need to pick a topic for which to create the stories. Choose the columns from the drop down menu, click Generate stories button and your stories will be generated on-the-fly.

2.4 Advanced Configuration

In Explorer you can configure different settings for your data analysis. These can be applied to the account as a whole or to individual projects.

Here each of the settings is explained briefly:

To apply any of these settings to an individual project, this can be done from the project edit page.

However, if you wish to apply settings to projects across the whole account, you can go to the Account page from the main Explorer screen. Each time that you make changes to your account, they will be applied to any new project which is created. For pre-existing projects, account settings will be applied the next time you explore. However, if there are project level settings already in place, these will override the general account settings.

3 Overview of the Gavagai Explorer GUI 

When Gavagai Explorer completes analyzing your data at each iteration, it presents the result in a GUI (Graphical User Interface). The GUI is divided into three main sections. At the top of the GUI you can find the configuration panel where you can apply a template model to your project, set up filtering conditions and remove terms from your analysis. Under the configuration panel, on the left, we have the working panel where you can interact with the system and your data. Finally, on the right we have the Details Panel where you can see the results of your analysis with details.

3.1 Overview Of GUI Functionality

3.1.1 Main Project Panel

In the top left hand corner of the Explorer GUI is the main control panel for project level settings. Here you will find important buttons that you need to use continually when analyzing data with the Explorer. If you know how to use these buttons correctly, it will help you to analyze your data with Explorer more easily.

3.1.1.1 Update and Save Button

Whenever you make changes in the working panel or configuration panel, these changes will not be applied until you press the ‘Update and Save’ button or the ‘Explore’ button. Note that you can make multiple changes in both the working and configuration panels between each iteration and all of these changes are subsequently applied the next time you press ‘Explore’ or ‘Update and Save’. For ease of access, the ‘Explore’/’Update and Save’ button has been placed in three different areas of the GUI; at the bottom of the configuration panel and at the top and bottom of working panel. Note that the functionality of all three of these buttons is the same, regardless of the name.

3.1.1.2 Undo Button

When you make changes in the working panel but before you press the ‘Explore’ button, Explorer will keep track of the current changes and provide you with an ‘Undo’ button that can be used to reverse changes sequentially. Keep in mind that once you have pressed ‘Explore’ and moved on to the next iteration, you cannot automatically reverse the changes using this button. The ‘Undo’ button can be found at the top of the working panel.

3.1.1.3 Sort Alphabetically

The default behaviour of the Graphical User Interface is to sort topics by descending prevalence (i.e. the number of texts in which they feature). By checking the ‘sort alphabetically’ box you can choose to instead sort your topics by alphabetical order. Topics inside a group will also be sorted alphabetically within that group.

3.1.1.4 Group Pinned Topics

If this box is checked, topics that you have pinned will be shown at together at the beginning of the topic list. Unpinned topics will follow. (For more information on pinning and unpinning, see the section below on topic level buttons).

3.1.1.5 Show Only Pinned Topics

Checking this box will display only the pinned topics in your project. Unpinned topics will be hidden.

3.1.1.6 Show Only New Suggestions

For every topic in your project, the Explorer suggests additional terms from your data which could also be relevant to your topic. As you progress with your exploring, it is likely you will add extra terms to your topics as you see fit. As the suggestions for a topic are based on the terms it already contains, new suggestions will occur each time you save and update your project (assuming new items have been added). Checking ‘only new suggestions’ will make the interface display only the suggestions that are based on the most recently added terms, hiding those that have already been seen.

3.1.1.7 Coherence For Suggestions

As previously mentioned, the suggestions for any particular topic are based on words that are semantically similar to the existing topic terms. As a result, as the number of terms in your topic gets larger, the number of suggestions increases. For larger topics, the list of suggestions can become very long. To make such a list easier to read, you can check the “coherence for suggestions” box. This means that the system will only display words that are semantically similar to a significant number of the existing topic terms, providing a more coherent list. Otherwise, the default setting shows words that are semantically similar to any single term in the topic.

3.1.1.8 Topic Size Distribution

At the bottom of the panel, you can find a small but useful info-graphic. Here you can see a rough overview of the current topics in your data and the distribution of their sizes, without needing to scroll down the list. You can easily see, for example, if you have many similarly sized topics, if you have just a few large topics and many very small topics, or other shapes of distribution.

3.1.2 Topic Level Buttons

Below the main project panel you can find the list of current topics. Each topic has its own small panel with buttons related specifically to that topic.

3.1.2.1 Pin Button

Each topic has its own pin button. When you pin a topic by pressing this button, it tells the Explorer that you want to always keep track of this topic in your list, regardless of its frequency. The Explorer usually displays the N most frequent topics, where N is customizable by the user (2.4: Advanced Configuration). The pinning functionality is particularly relevant when you filter texts, remove terms or add data. It can also be useful to keep track of a topic which is very small but very important. Other significant applications of pinning are when you create models from your existing projects (see chapter 8) or when you export the result of your analysis in a full MS Excel format (9.2 Save as Excel and Full CSV). Explorer will also provide Theme Wheels for your 6 most frequent pinned topics (6 Explorer Theme Wheels).

3.1.2.2 Topic Scroll Button

For each topic we have a topic scroll button in the working panel (see the previous picture). When you press this button the Details Panel will automatically scroll to the selected topic.

4 Topics in Gavagai Explorer

Topics are the core of the text analysis in Gavagai Explorer. They are basically the main subjects in your data. For instance, in hotel reviews, topics like hotel, staff, room, restaurant, etc. are usually among main topics. In addition, there are usually another type of topics in the texts which are not related to a hotel in general but become a topic for one specific hotel because of the frequent mentioning by respondents. For example, if you have a data including hotel reviews and many of the respondents refer to many items in the hotel as great items (e.g. the hotel, the restaurant, their room, etc.) then “great” becomes a topic in your project. On the other hand, if many of the respondents complain about a specific issue in the hotel; e.g. renovations, then that issue also becomes a topic in your project.

Each topic in Explorer has a name and it includes one or more terms. The topic name is a label assigned by the system or the user for referring to the topic, while the terms are the actual words (or sequences of words) from the data that the topic is composed of. Each term can be included in only one topic. We say a document includes a topic if it includes at least one of the terms in that topic. Then, the frequency of a topic is defined as the number of documents that include that topic, divided by the whole number of documents.

Explorer finds the main topics in your data and it makes it possible for you to revise them. When you run explorer on a dataset for the first time, Explorer shows you the 30 most frequent topics throughout all the texts.

For each topic, Explorer considers a specific area for that topic in both working and Detail panel. We refer to the working and detail panels as simply the topic area. In addition, there is a blue box for each topic in the working panel which includes the name of the topic. We refer to this box as topic box. At the right side of each topic box, you can see the topic expander which contains two numbers. Here you can see the topic box and its expander for the topic “hotel” for data including hotel reviews.

The first number (in green) is the number of including terms in that topic and the second one (blue) is the number of suggestions (see next section). When you click on topic expander you can see the including terms and suggestions.

In the following, we explain the main elements in each topic and we guide you through revising them.

4.1 Terms in Explorer

4.1.1 An Introduction to Explorer language Capabilities

4.1.1.1 Paradigmatic Neighbors

Explorer searches for terms in your data with more complexity than a simple search engine. Let us explain by an example. Consider the word “income” in the following sentences:

Many people are dissatisfied with their income.

I can’t get by on such a small income.

The company’s gross income grew considerably this year.

The single most important measure of a company’s profitability is net income.

Compensation is far below the market.

In the first two sentences, income has been referred to as a general term while in the two latter sentences the terms gross income and net income are specific types of income. In the last sentence, the word income is not present, but we have the word compensation which is a synonym of it. Words like income, net income, gross income and compensation are called paradigmatic neighbours. Paradigmatic neighbours are semantically related words which are used in text or speech for related objectives. Paradigmatic neighbours can be synonyms, like “income” and “compensation” in above examples. They can also be words that do not have same meanings but they are related in some way; e.g. “fork” and “spoon” which are both used for eating.

4.1.1.2 N-grams

An n-gram is a sequence of words which frequently appears in the same order in text or speech. Generally, it is important not to split n-grams as it might result in information loss. For instance, “water supply” is an n-gram consisting of two words “water” and “supply” while none of these words can define it individually. The word “San Francisco” is an n-gram which is different from both “San” and “Francisco”. Another capability of Explorer is to identify n-grams in your data and not split them. From now on, when we mention terms in this document we mean n-grams. The value of variable n is dependent on the corresponding language and it is usually between 1 and 3 or more.

4.1.2 Terms and suggestions

As mentioned, each topic can include one or more terms. Terms included in each topic are words that each can define that topic independently. Each term can belong to only one topic. For each topic, Explorer shows examples of texts including the terms in that topic. You can find them in explorer Detail panel. You can also filter the examples by clicking on specific term(s).

In the Detail panel, each term can be either selected (shown in orange), or non-selected (shown in green). When you explore a project, all terms in all topics become selected by default. You can deselect a term by clicking on it in the Detail panel. The examples and sentiments which are shown for a topic in the Detail panel are derived from the selected terms for that topic. Therefore, when you select or deselect a term, you need to press show sentiments and show examples buttons to see the updated results.

For the terms included in a topic, Explorer automatically finds their paradigmatic neighbours and shows them to you as Suggestions. You can see more suggestions by clicking on Get words button. When you hover over a suggestion in the working panel, a question mark will appear. You can see the examples of the texts including that suggestion by clicking on this question mark. When you add new terms to your topic, Explorer updates the suggestions list by adding the new possible suggestions. The number of new suggestions is denoted by a little red square under the total number of suggestions. In addition, the new suggestions are shown with a slightly different color from the old ones with a small red square at the top right side of them.

4.1.3 Adding and Removing Terms

4.1.3.1 Adding Terms

You can always expand your topics by adding new terms to them. To add terms, you need to open terms and suggestions by clicking on the topic expander. Then you can either click on suitable suggestions or write them manually in the terms entry field. An auto-complete drop down menu presents terms from topics and associations as candidates, and you can either select several options or add all of them at once.

To see more suggestions, you can click on Get words button. 

Note that a term including in one topic might appear in the suggestions of another topic. For instance, consider the the topic income including the terms “income”, “salary” and “salaries” and the topic compensation including the terms “compensation” and “compensations”. Since the two words compensation and income can be used interchangeably in the same contexts, you see the term “compensation” as a suggestion for the topic income.

And

In this case, if you choose to accept compensation for the topic income, Explorer will merge the two topics automatically (read more about merging in 5.2.3 Merging Topics). This is basically because the terms in each topic are assumed to be synonyms (so if two terms in two different groups are synonyms then all terms in that groups are synonyms). In figure below you can see the new topic income after automatic merging. The topic compensation will become disabled. The next time that you press Explore, you will see the new statistics for the new topic income and the topic compensation will be removed from the list.

The full search feature of the auto-complete drop-down menu presents terms from the project that are not yet members of any topic. As you type your auto-complete term, the full search finds all terms and multi-word expressions that match. Beware, however, that the search only finds multi-word expressions that the Explorer system knows about. This means that you cannot search for expressions that are two words or more unless these have been recognized as multi-word expressions in the system. Here is an example: the multi-word expression “san francisco” is a valid search term since it is so prevalent in ordinary language that our system knows about it as such. On the other hand “daniel san” is perhaps not as common and therefore a search for those two words will not get a hit even if the project in fact contains one or more texts with those words in sequence. Why not allow the search to find any arbitrary sequence of words you might ask. Similarly to much of the Explorer’s functionality in general, the full search feature is focused on finding the most important expressions as opposed to everything in detail. This design is a careful balance of utility and performance considerations.

Results from the full search are shown in the auto-complete drop-down menu under the heading “Full search”.

4.1.3.2 Removing Terms

You can remove terms from topics by clicking on them in the working panel. When you remove a term, you might still see it in the list of suggestions of other topics and therefore you can add it to them. Note that when you remove a term from a topic, Explorer automatically pins that topic so that you would not lose the topic in the list of topics in case the topic becomes infrequent.

You can also ignore a term from all of your topics by writing it in the text box under Ignore Terms in configuration panel and pressing add term (previous figure). When you remove a term, Explorer ignore it in your analysis, however, note that texts including that term are still available for contributing to the topics.

4.2 Associations

For each topic, Explorer finds the words that are tightly connected to the terms in that topic, and shows them to you as Associations. By tightly connected we mean words that appear together repeatedly and closely in the same sentences in different texts. For each topic, the list of associations to that topic can be found under the topic box. You can also find the frequency of each association with respect to that topic in front of it. Associations are ordered in the association list based on their frequency and also their closeness to the topics.

Associations can give you a better understanding of the topics. For example, consider the topic “the restaurant” which is a frequent term in a hotel reviews data set. As you see, the terms “closed”, “renovation” and “under construction” are tightly connected to this topic which means most respondents are complaining about renovations when they mention restaurant in their responses.

You might have noticed that the term “breakfast” is at the bottom of the list although it is more frequent in the topic comparing to the upper terms. This is due to the fact that  both frequency and closeness are taken into account in the process of listing the associations.

For any subset of the set of terms and associations of a topic, you can filter the texts examples that contain all the words in that subset. You only need to click on them in the detail panel to filter texts.↓

4.3 Sentiment Analysis

Gavagai Explorer applies word based or lexical based sentiment analysis principles to quantify the sentiments behind expressed opinions. In the Details Panel, you can see the quantity of three basic sentiments for each topic or group; that are Negativity, Positivity and Skepticism (next figure). When you filter texts by selecting terms and associations in the details panel, the sentiment values will be updated as well. When you export the result of your analysis into excel, you can see 8 sentiment values for each single text (see 9.2.2 Sentiments). You can also select one or multiple topics for sentiment analysis when you export. This will give the sentiment scores for your selected topics in the report (see 9.2.5 Sentiments Per Topic). Moreover, you can model your own sentiments by using Explorer Concept Modeler and then Explorer will analyze your data for these Concepts (read more in 7 Explorer Concept Modeler).

4.3.1 More about Sentiment Analysis in Explorer

Explorer performs two different types of sentiment analysis; new and classic sentiment analysis. Explorer selects the new sentiment algorithm by default. You can switch to the classic sentiment algorithm in your advanced configuration settings located on the Account page. The Explorer will strictly apply only one algorithm for the entire Explorer project. When you set an algorithm for your account, you must click Update and Save to apply the new algorithm.

The classic sentiment algorithm performs a sentence level sentiment analysis for each topic. The new algorithm performs a topic level sentiment analysis for the topics. More on both of these algorithms in 4.3.4 The Sentiment Analysis Algorithms that Determine the Score.

This difference is important when a sentence has different topics with different sentiments. If a sentence is so short and has only one topic: “The room is good”, then using either the new or the classic algorithm results in the same score.

4.3.2 The Sentiment Scoring System

The system’s sentiment scoring gives a score for each Sentiment word used to describe a topic. Note, amplification words such as “very” increase the score. And negations such as “not” impact the score by reducing the score.

For example:

The room was good. Has a 1 for Sent: Positivity.

The room was really good. Has a 2 for Sent: Positivity.

The room was not good. Has a 1 for Sent: Negativity.

There are eight sentiment categories: Skepticism, Fear, Violence, Hate, Negativity, Love, Positivity, and Desire. The categories avoid ambiguity of sentiment scoring by not containing words that can be inside many categories. For example, “cheap” could have different sentiments. For example, “X is cheap”. This sentence is ambiguous. If X is beer, it is positive, if X is a wedding ring it is negative. Thus, if there is a word that you believe should be in the sentimental category then please try to use the word in sentences that are both that sentiment and the opposite sentiment to check. In contrast, words such as “good” that express only one sentiment are added to their respective sentiment category.

When a word from the eight categories like, Positivity, for example “good” is used to describe a topic such as hotel. The sentiment score will give a simple 1 for the topic hotel. The sentence, “The hotel is good.” would receive a 1 for positivity, and 0 for the seven other sentiment categories. If you would like to see the actual numbers for the sentiment scores for each topic, you need to export the analysis as an Excel or CSV file and select the topic you would like to see. See 9.2.5 Sentiments Per Topic for more. The sentiment score given for each topic varies when combination of words happen such as “really good”.

4.3.3 The Sentiment Bar in the Web Application

In the web application the sentiments are in the right hand side with a percentage breakdown and also in absolute values. We see the sentiments Negativity, Skepticism, and Positivity in a bar. This sentiment percentage bar is calculated by using the topic that the percentage bar is referring to. All the topic’s Positivity, Negativity, and Skepticism scores are summed. For each sentiment category this sum can be found next to its name above the sentiment bar. Then, each of Positivity, Negativity, and Skepticism scores are divided by the sum to return a percentage. To see the text examples which are relevant to one specific sentiment category, you can click either on its name or on its color in the bar. It’s also possible to change basic sentiments in the bar to any other sentiment Gavagai Explorer supports: Love, Hate, Violence, Desire, Fear. You can even have Neutral sentiment calculated and shown in the bar - this can be adjusted in Project Settings or Account Settings. See 2.4 Advanced Configuration.

4.3.4 The Sentiment Analysis Algorithms that Determine the Score

Consider the following text uploaded to The Explorer:

The text include two different topics and for each topic there is a different opinion. The new sentiment algorithm has more precision in getting the expressed opinions for individual topics and calculating the sentiment scores. The room topic has a 1 for positivity. And the staff topic has a 1 for negativity. Looking at the web application there is 100% positivity for room and 100% negativity for staff.

Moreover, for the new sentiment algorithm, not all topics are relevant for sentiment analysis. Explorer only performs sentiment analysis for topics (or topic terms) that are not sentiment terms themselves.

Consider the sentence “The room is nice”. If we ask what is the expressed opinion about room in this sentence, one can say it is positive, it is nice. Now suppose that instead of room we focus on nice as a topic. Does it make sense to ask “what is the expressed opinion about nice in this sentence”? The answer is no. In fact nice is not a focus topic in this sentence. The sentence is explaining room and not nice. Nice is the word by which the sentence expresses opinion about room. This is the reason behind why we do not perform sentiment analysis for sentiment terms.

The classic algorithm takes into account sentimental words of an entire sentence. Regardless of what topics the sentimental words are describing. For example, the sentence, “The hotel was good and the staff are good.” will return a 2 for positivity for the topic hotel and the topic staff. Thus, there is less precision in analyzing the sentiment. In addition, for the web application, the detail panel will only display sentiment when 10 texts have sentiment for a topic.

The sentence uploaded as an excel file to The Explorer (repeated 10 times since we need at least 10 texts):

returns for the topic room, 1 for Positivity and 1 for Negativity. And in the web application, we see the topic room have 50% Negativity and 50% Positivity. This is a coarse approach and can be inaccurate in calculating sentiments for topics.

However, there are some benefits. The classic algorithm is useful for calculating what the sentiment is on a sentence level is. Which is important for comparing individual documents. In addition, there is a slight speed advantage.

4.3.5 Sentiment Analysis and the Text Examples in the Web Application

In the web application and in the detail panel, Explorer shows examples of texts which are included in the topics. These texts are examples featuring the terms of the topics selected in the detail panel (shown in orange). At the top of each example area, Explorer shows sentence(s) that feature the topic terms with bullet points. To the right hand side of each sentence, their topic related sentiments are shown by colored circles, where each color shows the same sentiment as in the sentiment bar. You can see the complete texts by clicking on ‘Show original text’ at the bottom right corner of the examples. Here you can also see the sentiments found in the entire text (not specific to the particular topics). Note that Explorer only shows those sentiments that you have chosen in your project.

4.3.6 Overall Sentiment of the Project

At the top of the detail panel and under Project Summary, we have the overall sentiment of the project shown in a colorful bar. This feature is dependant on your active sentiments, your sentiment settings and the neutral sentiment if it is on or off. Based on these settings and the contribution of each verbatim to each sentiment, the percentage of each sentiment is calculated for all verbatims. Each time that you load/re-explore a project, you need to click on show sentiment button to see the sentiment bar. Here you can also see text examples by clicking on the show examples button, and you can filter the examples for a specific sentiment by clicking on the related color on the sentiment bar.

4.4 More about n-grams in Explorer

Now that you have learned about topics, topic terms and sentiment analysis, it is worth learning a bit more about n-grams in Explorer as well. As mentioned before, n-grams are topic terms including multiple words, for example “San Francisco”.  Explorer identifies n-grams in your data and show them to you as topics if they are enough frequent. You can also add n-grams to your topics manually. The most important characteristics of the n-grams is that they are treated as one single entity, and therefore, the uni-grams included in an n-gram cannot contribute to topics individually. This is the case for both topic counts and sentiment analysis. As an example, suppose that you have an n-gram “junk food”. Also assume that you have a topic FOOD which includes “food” as a topic term but not “junk food” as a topic term. Now for the sentence “I don’t like junk food at all”, for Explorer the topic FOOD is not included in this sentence because of “junk food” being a bi-gram. 

5 Revising Topics

In this section, it is explained how to revise your topics by Explorer according to your assumptions and needs.

5.1 Adding and Removing Topics

5.1.1 Adding Topics

You might be interested in specific topics which are not frequent enough to appear in the list of topics. You can add these topics to your project manually and Explorer will analyze your data for them with a semantic search.

You can add topics by clicking on the Add Topic button in the top of the working panel. When you click on this button, Explorer considers a new topic area for it at the top of the list. Here you can give a name to your topic, and you can add terms to your topic by writing them in the text box and clicking on Add words. When you are done, click on Remove me after adding words.

Note that the name of the topics are only labels that are assigned to them, and therefore each topic should have at least one term. Terms are the exact words the Explorer actually keeps track of in your data. You cannot add a term which is already included in another topic. The new topics are automatically pinned, so Explorer keeps them in the list regardless of their frequency.  

Keep in mind that Explorer does not add these new topics to your analysis until you have pressed the ‘Explore’ button.

When you add new topics to your project and press Explore, Explorer starts re-analyzing data and it inserts new topics into the list of topics in order of their frequency. Then, you can see the information about associations, suggestions and statistics for new topics.

Note that Explorer does not remove any topics from the list when you add new ones.

5.1.2 Removing Topics

You can also remove a topic from your analysis if you find it unimportant for your project. Hover over that topic in the working panel and click on cross button to remove the topic.

Explorer will ignore the topic when you remove it from the list, however, note that texts including that topic are still available for inclusion in other topics. The terms including in each topic are saved in configuration panel under the Ignored Terms, and you can have them back at any point by clicking on them.

5.2 Grouping and Merging Topics

5.2.1 Select button

When you hover mouse over a topic in the working panel, an upwards arrow appears inside the topic box which is called Select button. You select a topic by clicking on this button. When the topic is selected, the topic blue box turns to orange. You can also deselect the topic by re-clicking on this button.

In Explorer, both merging and grouping should start with selecting a topic. In the following it is explained how we can merge and group topics by Explorer.

5.2.2 Grouping Topics

5.2.2.1 Intro

If you find some topics to be in the same category you can put them in one group. This will give you a more organized working panel. In addition, Explorer will tell you about the sentiment and statistic of the whole group.

For instance, for the hotel reviews, you might like to put all the words about food (e.g. breakfast, coffee, wine, etc.) in one group called Food. Explorer shows you the number of the respondents that have written about food (frequency of the whole group). It also shows you the aggregate sentiments of this group, so it wil let you know if the respondents are positive or negative about food on the whole.

5.2.2.2 How To Group

Grouping topics in Explorer starts with selecting one single topic by clicking on Select button. When you click on this button, a down arrow button will appear in the left side of each topic or group. We refer to this button as Group button. You can place the selected topic into a target group by clicking on this button. By default, the name of the group will be the name of the target topic (or group). You can change this name by re-writing it in the working panel.

The new groups are automatically pinned, so Explorer keeps them in the list regardless of their frequency.

5.2.2.3 Statistics

After re-exploring data by Explorer, grouped topics are inserted into the list of the topics in order of their aggregate frequency (which is the number of distinct texts that include at least one of the topics divided by the whole number of topics). This value can be found in both working and detail panel under the group name. In the detail panel and under each group name, you can also find the aggregate sentiment of that group. The frequencies, sentiments, associations and suggestions for single topics can be found under their names like before.  

5.2.2.4 How to Ungroup

You might want to take a topic out of a group. You can click Undo button at the top or click the ungroup button. Note that the topic you ungroup from a group will be automatically pinned. You should update and save after.

5.2.3 Merging Topics

5.2.3.1 Intro

In case that you find two topics equivalent you can merge them to one single topic. This is mostly the case if the terms in two topics are synonyms or paradigmatic neighbors. For instance, for two topics income and compensation including the terms income and compensation successively, you might merge them to get a single topic including both the terms income and compensation. Merging topics increases the strength of the resulting topic in terms of the number of texts that are included in the topic and therefore it results in preciser sentiments and more informative associations.

5.2.3.2 How to merge

Similar to grouping topics, merging topics starts with selecting a single topic. As before, you select the topic by clicking on the Select button in the topic box. When the topic is selected, an upwards arrow button will appear at the left side of all other topics. We call this button as Merge button. You merge the two topics by clicking on the Merge button for the second topic. By default, the name of the merged topic will be the name of the first selected topic. You can change this name by re-writing it in the topic box.

5.2.4 Topic Coverage

If you choose to you enable it (section 2.4), you can receive details about how much of your data is covered by the topics in your model. This can be useful to help you understand how complete your analysis is.

When the setting is enabled, an extra topic is featured at the end of your topic list. It is always labelled ‘Unclassified’. It shows the number of texts which are not included under your current topic analysis, both as a percentage and as an absolute number. The magnitude of this figure often depends on the characteristics of an individual dataset. It is also possible to get examples of the texts which are unclassified and get a sentiment score for this special topic (in the usual manner). This should aid with an understanding of what data it is which is not currently being covered.

6 Explorer Theme Wheels

As mentioned before, Explorer represents an statistical visualization of your first 6 pinned topics (or groups) by Explorer theme Wheels. At the top of each theme wheel, you can find the name of the corresponding topic. The frequency of the topic can be found in the center of the wheel. The pieces of the wheel are the four most frequent associations of the topic. If you hover over a piece you can see the frequency of the corresponding association inside the topic.

Here you can see the theme wheel regarding the topic “room” in hotel reviews. The topic has a frequency of 75.4% in the data and its most frequent associations are “great”, “clean”, “comfortable”, and “staff” respectively. The frequency of “great” as an association of “room” is 39.8%. This means that almost 40% of the people who have mentioned room in their responses have found it great.

7 Explorer Concept Modeler

The Concept Modeler is a tool for additional analytics in Gavagai Explorer. You can define different concepts in Explorer and then analyze your data with respect to them. Same as models, concepts are independent from projects and one concept can be used in different projects. A concept is defined by its including terms. In contrast with topics, the including terms in a concept do not need to be synonyms or semantically similar terms, but they are elements that jointly define that concept. Let’s give an example.

In Hotel Reviews you might define a topic called breakfast, including the terms “breakfast” and “the breakfast”. Each of these terms that appear in a text we will know that the topic breakfast is included in the text. Now consider the two following sentences retrieving from texts:

None of the words “coffee”, “latte”, “croissant” or “mornings” can define the topic breakfast independently; as the case in the first sentence, but a combination of these words can tell us that the text might be related to the concept breakfast; as the second sentence.  

Therefore, the concept breakfast can be defined by set of words like {tea, coffee, latte, bread, cheese, jam, morning,…}. You can start defining the concept by a few most necessary words. Then Explorer will show you more suggestions to be added to your concept.

7.1 How to Create and Edit Concepts

To start creating a new concept or editing the old ones, you can click on My Concepts in Explorer navigation bar to be redirected to concepts page. In this page you can see the list of all of your concepts that you have previously created. To create a new concept, click on Create concept button. You will be then redirected to your new concept’s page. Give a name to your concept by writing it in the “Concept name” text field and select the language of your concept. Add terms to your concept by writing them in “Keywords” text field and add them by pressing the add button. When you are done with adding the most necessary terms for your concept, press the Create Concept (and get suggestions) button to save your concept and get new suggestions.  

7.2 Different Types of Concepts in Explorer

Conceptually, you can define two different type of concepts in Explorer and choose between them for different usage. We refer to these concepts as Topical and Sentiment-Based Concepts. Topical Concepts are those Concepts that define a specific topic or subject while sentiment-based concepts are those concepts that define specific feelings or opinions towards topics. For example, the concept Breakfast that we defined above can be considered as a topical concept. Then you can define a sentiment-based concept like “positivity” and put terms like nice, delicious, tasty, etc. in it. In next section we show how you can measure a sentiment-based concept like “positivity” for a topical concept like Breakfast.

7.3 How to Use Topical and Sentiment-based Concepts in Explorer

When you want to export your project to Excel or CSV, in the report configuration box, you can tell Explorer to analyze your data for the concepts you have already created (for exports see 9 “Export as” Button and Exporting the Result of your Analysis). Here in the configuration box, you have two options for analyzing concepts; target concept and concepts to analyze:

7.4 Creating Concepts from Topics

In Explorer it is possible to create a concept from a topic. When you open a project, in the left panel of the GUI and for a topic of your choice, you can click on Edit terms button which is located next to the blue topic box.

Then, in the top right corner of the grey area, there is a button for creating a concept from your topic. When you click on this button, a confirmation pop up will appear and after you click ok, Explorer creates a concept from your topic. The concept has the same name as your topic and same terms as your topic terms. When your concept has been created, you can choose to either stay in your project page or go to that concept page to edit it.

8 Models in Gavagai Explorer

You can save a project in Explorer as a model and then apply the model as a template for other projects. Using models is a suitable approach when you analyze similar types of data frequently and you have same concerns in your analysis; for example, you are looking for the same topics or themes. Here we explain models in Explorer and we guide you through creating and using them. However, if this is the first time that you are reading this document, we recommend you to skip this section for a little while and return to it after reading other parts of the document.

A model consists of your general Topic structure in the project you are Exporting your Model from; meaning grouped topics, merged topics, pinned groups and topics, and your ignored terms. When you apply a model on a project, the project current model will be replaced by the new one. Therefore, if you are unsure, you would better save the current model first.

Note that to apply a model to your project, the project’ file does not need to have the same specifications as the model’ source file (e.g. same columns or same number of texts, etc.).

8.1 Creating and Applying a Standard Model in Explorer

8.1.1 Create Standard Models from Projects

You can create a model from a project by selecting Standard under the ‘Save Model as’ drop-down menu in the working panel. The Model saving function works much like the save feature in a computer game: the current state of your analysis at the time when you pressed save is stored in the system memory and this configuration can be applied to any existing project. Once your model has been created, you can navigate to the ‘Models’ page and rename it to something informative so you can keep track of it easily.

8.1.2 Upload Models

You can also upload a model from your computer and use it in different projects. The Upload Model button can be found in Models page. Please note that a file should be in Excel or csv format.

8.1.3 Applying a Standard Model to a Project

Any saved model can be applied to any other project. During the initialisation phase of a new project you can find the model under Apply the model drop-down menu in configuration panel. Or by scrolling up from the main Explorer interface of an existing project, you should be able to find this screen:

Another way of applying a model to your project is to find the ID of another project from the browser’s address bar (the last segment in the URL), and enter it in the provided text field.

8.2 Sharing a Model

It’s also possible to share a model with your colleague so that they can use it in their analysis. Go to Models, click on Share button and insert the e-mail address of the colleague you would like to share the model with. They should receive a notification and there will be a pop-up message in their account saying that a model was shared with them.

8.3 Dynamic Models in Explorer

A Dynamic Model is an extension of Standard model with some additional functionality. A Dynamic model is always available in the context of a Master project and each time the project is updated, the corresponding Dynamic model is versioned and updated as well.

8.3.1 Creating a Dynamic Model

In Explorer you can create a Dynamic model from a project by selecting Dynamic under the ‘Save Model as’ drop-down menu in the working panel.

We refer to this project as Master project. You can apply a Dynamic model to other projects. We refer to a project which is dependent on a Dynamic model as a Dependent project. When you make changes to the Master project, these changes will be automatically applied to its Dynamic model and will also update all Dependent projects to which the Dynamic model is applied.

8.3.2 Applying a Dynamic Model to a Project

You can apply a Dynamic model to a project in the same way as a Standard model (see 8.1.3 Applying a Model to a Project). Every Dynamic model will be prefixed with ‘(DYN)’ to indicate that it is a Dynamic model.

We refer to a project which has Dynamic model applied to it as a Dependent project. When you make changes to a Master project, the connected Dynamic model will be updated. For each of the projects dependent on the Dynamic model, you will receive a notification in the projects homepage indicating that these projects are out of date and you need to re-explore them to get their latest version. Also when you load these projects, the explore button is active and Explorer reminds you that a new version of the model is available and that you need to re-explore the project.

You can apply a Dynamic model to a project which has a different language than the Master project (from which the model was created). In this case, the pinned topics terms in the model are translated to the language of the Dependent project. The topic labels, however, are retained in the language of the Master project.

Note that if you apply a Dynamic model to a project, it would not be possible anymore to make any changes to the model of the project except for editing the terms inherited from the Dynamic model. Note that you can still apply and change project settings.

8.3.3 Editing a Dynamic Model

After you have created a Dynamic model, you can find it in the list of models in models page with an indication that the model is Dynamic.

If you are the user who created the Dynamic model, you can see the previous versions of the model in the model edit page. You can revert the model to an older version by clicking on revert button. This will also revert the corresponding Master and Dependent project accordingly.

In the model edit page, you can also see the list of projects which are dependent on the Dynamic model.

8.3.4 Sharing a Dynamic Model with Another User

You can share a Dynamic model in the same way as a Standard model (see 8.2 Sharing a Model). The user to whom the Dynamic model has been shared will see an indication that the model is a Dynamic model.

8.3.5 Deleting a Dynamic Model

If you delete a Dynamic model, its corresponding Master project and all Dependent projects will be disconnected from the model. Note that the Master project and Dependent projects will still have the latest version of the Dynamic model but now you can work with these project as regular projects.

8.3.6 Deleting a Master Project

If you delete a Master project, its connected Dynamic model will be disconnected from the project (the model gets converted to a Standard model) and all Dependent projects will also be disconnected from the Dynamic model and will become like regular projects. So you can work with them as usual.

9 “Export as” Button and Exporting the Result of your Analysis

After each iteration and before you make any changes to your project, Explorer provides a Save as button where you can save the current result of your analysis in different formats. Under Export as drop-down menu there are 4 options; PDF, Excel, Full CSV and Model.

If you want to have a brief report of your analysis similar to what you see in Explorer GUI, you can save your project as either PDF or Excel. In case you want to have a detailed result of your analysis with respect to individual texts, you can choose Excel or Full CSV.

When you choose the format, a message box will pop up (next figure). You can either choose to be redirected to the project edit page where you can download your file or you can do it later by pressing Ok. The project edit page can be accessed from Explorer homepage (My Projects page) by clicking on Edit page button for that Project as on the figure below.

9.1 The Project Edit Page

The Project Edit Page is where you can see and change information about a project:

9.1.1 The List of Reports

In this list you will see entries for all reports created in the project. If a report is in progress it will be printed in black, and once it is finished it will become red and clickable; to download a finished report you click the report name. You can also delete a report by clicking the trash can icon at the right of the report entry (you will be presented with a confirmation pop-up to ensure you don’t delete a report accidentally).

9.2 Save as Excel and Full CSV

If you select an Excel or CSV format, then you have the option to configure a number of extra parameters in your report.

Topics can be sorted alphabetically or by frequency (default option). Keywords can be included or not. You can choose which concepts to analyze and which topics to count sentiment for. A target concept for the whole report can also be set.

When you download the result of your analysis, aside from the summary tab, you you also will have a data tab containing your original data appended by the analysis result from Explorer. Since all cells are handled as text, eventual metadata specifying the cell type is lost as well as any eventual formulas existing in the original excel file. If the meta-type of a number column is important for you then just export the report in a CSV format and use the import function in excel to create an excel version of the report. Excel normally interprets the text containing a number as a number type, given it is according to the format of the excel application importing the CSV file. Explorer performs a row based analysis of your data in respect to your pinned topics, target concepts and sentiments, and for each text it adds the result of the analysis to the corresponding row. In the following we explain the appended columns.

9.2.1 Pinned Topics

The first added columns are the columns regarding to your pinned topics. You can see the name of each pinned topic in a header of a column. A cell in a topic column contains 1 if the corresponding text includes that topic, and 0 otherwise.

9.2.2 Sentiments

The next added columns are the ones containing sentiment scores. Explorer measures 8 standard sentiments for each text; they are: SENT: DESIRE, SENT: FEAR, SENT: LOVE, SENT: POSITIVITY, SENT: SKEPTICISM, SENT: NEGATIVITY, SENT: HATE, SENT: VIOLENCE. If you have Neutral sentiment feature on (see 2.4 Advanced Configuration), then there will be a column for NEUTRAL as well. You can see their names on the header of the columns. Each cell in a sentiment column contains the score of that sentiment for the entire corresponding text. In case you have selected a Target Concept for the analysis of your project, the sentiment scores will be restricted to the sentences that contain at least one of the terms in any of those concepts.

9.2.3 Target Concepts

The next columns are the target concepts that you have chosen to include in the report. The Explorer will append two new columns for each target concept. For each target concept, there is a column in the Excel file having the concept name in its header. Each entry in a concept column is the number of distinctive terms in that concept that are included in the corresponding text. The other column is the sentences that appeared in the corresponding text.

9.2.4 Concept to Analyze

You can select your sentiment-based concepts under “Concepts to Analyze”. In this case, Explorer computes the strength of each concept for each text and shows them to you in new columns, one for each concept. Here the computation is performed in the same way as for Explorer built-in sentiments (see 4.3.2 The Sentiment Scoring System) which will always use aggregated settings (as opposed to binary settings).

9.2.5 Keywords

The next columns in the report are the keywords columns. Keywords are those terms that best describe the subject of the texts. There are 4 different keywords columns in the Excel report:

9.2.6 Sentiments Per Topic 

For a selected topic, you can gauge the sentiment in each individual text and add a column for each sentiment to the report. For instance, if you select a topic after clicking the Export as Excel or CSV dialogue box to bring up the Configure Report Box, each text in your project will be analyzed with respect to the Positive, Negative, and Skepticism sentiment around the topic, and the columns for the sentiment scores of the specific topic(s) chosen will be added to the resulting Excel file under the name Sent: Positivity(topic name).

This is useful when you want to compare the positive sentiment score of the verbatim – located in the usual column called SENT: POSITIVITY. With the topic’s positive sentiment score – located in the new appended column called SENT: POSITIVITY (what ever topic you chose). For example, if your topic’s positive sentiment score is very large and almost as large as your verbatim sentiment score. Then there is a strong indication that the topic is driving the positivity of the verbatim.

*note adding a lot of topics to analyze will add thee columns per topic. Thus, the report generation time will be affected, the more topics are selected.

The Sentiments per topic and per verbatim are used in the Driver PDF report. 

9.3 Drivers report PDF 

Satisfaction Drivers is a new form of report on the base of Explorer’s best features that provides an effortless and efficient “one click” analysis highlighting satisfaction drivers in survey responses, reviews, etc. It’s quick, easy, and doesn’t require any additional user input.

In the other words, it gives a direct answer to the question “What drives respondent satisfaction?”.

The “one click” functionality is accessed directly from the Explorer start page. After an Excel file with at least one text column is uploaded, the project is created and explored. It is also possible to generate a Satisfaction Drivers report by choosing “Driver (PDF)” in the “Save as” drop down menu in your existing projects.

The report will show a simple and neat visualisation of a handful selected drivers from the given datafile - both positive and negative (if applicable).

The axes of the diagram are: Y axis - correlation to overall satisfaction, X axis - driver satisfaction ratio (in %). Each bubble represents one driver, based on the analysis of topics and their associations. The drivers’ position on the diagram represent their importance and meaning for the customer satisfaction.

Top drivers: The average net satisfaction rate for a driver. Both positive and negative sentiments are used to judge the satisfaction of a driver. Ratio: The ratio of texts that contain a driver where the average net satisfaction rate is positive/negative. Correlation: The correlation between driver sentiment and overall sentiment. Occurrence: The amount of texts in that the satisfaction driver occurs.

9.4 PDF 

This is a PDF report that mirrors the web application. It will show the Groups, Topics, Terms that build up a Topic, and the Associations for each Topic. This is useful way to share the report.

10 Adding Data to your Project

In Explorer you can add data (more texts) to an existing project by uploading a new Excel/csv file in the project edit page. The file needs to have the same columns as the one you initially uploaded and should not contain a header column. You can also see your upload history on this page.

11 Payment System

Gavagai Explorer offers two different types of payment methods: credit card payments and invoicing. When the Trial period has ended, you can reactivate your account on Account page and either submit your credit card details or contact our customer support, so that we can set up invoice payments for you.

11.1 Credits

Each row in your uploaded file corresponds to one credit charged to your account. As soon as you hit the ‘Explore’ button for the first time for a given project, the corresponding credits will be deducted. This means that if there is an error with your file during the upload process, you won’t be charged, as you have not been able to proceed to the exploration phase.

You can check the number of remaining credits you have on the “Account” page.

11.2 Plans

Our payment plans are based on a subscription format, with a tiered number of credits included per month. On creation, your account will be automatically assigned to a one month free trial with 2000 texts. You can switch to a plan which is more appropriate to your exact needs at any time. The equivalent price per credit depends on your current plan.

More specific details of the account plan tiers can be found on our Pricing page.

11.3 Upgrading Plans

If you upgrade to a higher plan during a given month, you will only be charged for the price difference between the high and the lower plan. However, remember to take into consideration the time remaining in the current month. It may not be wise to upgrade to a large plan with only a couple of days remaining to use it. The payment system allows the user to manually enter the number of credits for the plan, but the charging is still carried out at the next tiered level. Care should therefore be taken to enter a valid amount. For example, entering 10001 credits rather than 10000 will lead to a 20000 credit charge (the next highest plan).

11.4 Downgrading Plans

If you would like to move to a lower plan for a subsequent month, be sure to make the changes before your payment date (although after you have used all needed credits from the higher plan).

11.5 Overage

If you don’t have sufficient credits to explore a new project, you have the option to buy them on a per project basis rather than changing plan. This may be of use to you if the step up to the next payment plan is too large an increment for your needs.

Just create and explore a project and you will be presented with the option to accept an overage charge. The extra usage will be charged at the same price per credit rate as your current plan. 

Enter the word “ACCEPT” into the text field and click on the “Accept” button to accept the charges. You will be charged immediately if you have a linked credit credit card. If you are paying by invoice, the charges will be added to your next statement.

11.6 Deactivated Accounts

If you decide to cancel your plan completely or your account goes unpaid, your account deactivation will behave as follows. For a duration of 30 days after the cancellation date / payment default comes into effect, there is a grace period. You will have access to your existing account projects but you will not be able to create any new projects or upload any new text. Then, your account will become frozen for a further period of 90 days, during which you will not be able to access any projects, data or previous analysis. At the end of this freeze period, all data will be deleted. You can reinstate your account at any time within these 120 days by purchasing an active plan.

12 Sharing Credits by Managing Users

You can collaborate with other users and share your credits with them. This way, all of your colleagues or partners can use their own Explorer accounts, but only one of the account has to provide billing information and will get charged.

12.1 Inviting Users

You can invite other users via the Account page. Scroll down until you see the following, and click on “Invite user” to invite another user to be managed by you. This user will then get a notification via e-mail and can accept the invitation when they log into their account.

12.2 Disconnecting Managed Users

On the same page, you can also remove managed users.

12.3 Disconnecting from Manager

As a managed user, you can go to your Account page at any time and disconnect from your manager.

13 The API

If you are a developer and want to access Explorer’s API, you can do so with the credentials from the Explorer web application. You don’t need anything else, so no API key, etc.

Here you find the developer documentation: Gavagai Explorer API Documentation

For a tutorial on how to get started with the API, refer to this page: Gavagai Explorer API Tutorial