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.
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.
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.