Sentiment analysis encompasses a range of computational techniques for detecting and quantifying the presence of affect and emotion in written texts. In this essay, I use the techniques of critical code studies to offer a case study of one such sentiment analysis tool called TextBlob, about which I advance two intertwined claims. First, I map TextBlob’s reliance on a web of programmatic and textual dependencies, and how in turn, TextBlob effaces these dependencies’ formal specificity in the service of computational processing. This effacement supports my second claim: that TextBlob, and sentiment analysis more generally, models affect as programmatically latent in the smallest particles of language, which it then seeks to make available for computational processing. I explore the consequences of this computational model of affect for digital humanists seeking to integrate sentiment analysis and similar tools (including AI/LLMs) into their work.
Jeffrey Moro (Mon,) studied this question.