Lexicon-Based Sentiment Analysis in Behavioral Research
Free sentiment code can turn piles of words into quick mood data for any verbal-behavior case.
01Research in Context
What this study did
Cero et al. (2024) wrote a how-to paper.
They show BCBAs how to run free sentiment-analysis code on any text.
The code counts positive and negative words in therapy transcripts or social-media posts.
No new experiment was run; the paper is a roadmap.
What they found
The authors found that open-source tools can score verbal behavior in minutes.
Manual coding that used to take hours can now finish during a coffee break.
Starter Python scripts are shared so you can copy-paste and start today.
How this fits with other research
Belisle et al. (2019) also measured verbal behavior, but they used lab tasks and pen-and-paper scoring.
Cero’s code replaces those slow steps with instant word counts, extending the same idea into big data.
Eugenia Gras et al. (2003) warned that measurement tricks can pick up "nonspecific" noise.
Cero answers by showing how to clean text first, keeping the signal you actually want.
Sayers et al. (1995) pushed for math-based analysis of human talk; sentiment scores give exactly that kind of number.
Why it matters
You can plug the scripts into your next parent interview, staff meeting notes, or client’s Twitter feed.
Instant mood graphs help you spot problem days early and show progress to funders with hard numbers instead of gut feelings.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Paste the paper’s Python script into a free notebook, feed in last week’s session transcript, and graph the sentiment slope before your 9 a.m. meeting.
02At a glance
03Original abstract
A complete science of human behavior requires a comprehensive account of the verbal behavior those humans exhibit. Existing behavioral theories of such verbal behavior have produced compelling insight into language’s underlying function, but the expansive program of research those theories deserve has unfortunately been slow to develop. We argue that the status quo’s manually implemented and study-specific coding systems are too resource intensive to be worthwhile for most behavior analysts. These high input costs in turn discourage research on verbal behavior overall. We propose lexicon-based sentiment analysis as a more modern and efficient approach to the study of human verbal products, especially naturally occurring ones (e.g., psychotherapy transcripts, social media posts). In the present discussion, we introduce the reader to principles of sentiment analysis, highlighting its usefulness as a behavior analytic tool for the study of verbal behavior. We conclude with an outline of approaches for handling some of the more complex forms of speech, like negation, sarcasm, and speculation. The appendix also provides a worked example of how sentiment analysis could be applied to existing questions in behavior analysis, complete with code that readers can incorporate into their own work.
Perspectives on Behavior Science, 2024 · doi:10.1007/s40614-023-00394-x