The Lexical Suite analyzes people's language in order to understand their underlying opinions.
It packages together the Evaluative Lexicon with the all-new Certainty Lexicon. It keeps the original ability to measure the emotionality, valence, and extremity of people's opinions and now also captures the confidence people have in their opinion.
It’s free for academic use and available for Windows and Mac.
Want to give it a shot?
Despite the recent explosion of sentiment analysis - tools that measure people's opinions in natural language - an overwhelming majority of these tools measure only the simplest facet of consumer sentiment: whether it's positive or negative.
But could this focus lead us to miss out on other critical information?
Our research finds that words have the ability to tell us so much more about people's opinions. We created the Lexical Suite (LS) to move sentiment analysis beyond positivity to measure not only positivity, but also the extremity, emotionality, and confidence (certainty) of people's opinions.
The LS can be used with natural text in any form, including newspaper articles, online reviews, Twitter and Facebook posts, and transcribed audio.
The tools that make up the Lexical Suite were created by Matt Rocklage, Russ Fazio, Derek Rucker, Loran Nordgren, and Sharlene He.
Interested in learning more? Read all about the LS in our academic publications on this webpage or download it below.
The software can utilize TXT, CSV, and Excel files and can analyze millions of full-text records.
We hope that the program itself should be intuitive to use, but we've created a document that guides you through each variable the LS calculates (link).
See our academic publications (Evaluative Lexicon, Certainty Lexicon) which provide more detail on how we constructed and validated the LS tools as well as pointers on how best to utilize the measured variables.
The LS was specifically designed to be a general text analysis tool - one that focuses on a person's opinion and on language that is used consistently across a large range of topics. In that regard, the LS emphasizes accuracy over absolute coverage and thus will not code a piece of text if it does not contain an LS word. See this chapter we wrote as an example of the tradeoffs of the different text analysis approaches (link, pp. 18-20).
We have tested the software extensively, but it is still in beta so please let us know if you run into any issues by e-mailing Matt Rocklage at m.rocklage@northeastern.edu.