Abstract
This paper is concerned with theoretical considerations of commercial content analysis software, namely Linguistic Inquiry and Word Count (LIWC), developed by social psychologists at the University of Texas. LIWC is widely cited and forms the basis of many research papers from a range of disciplines. Here, LIWC is taken as an example of a context-independent, word-counting approach to text analysis, and the strengths and potential pitfalls of such a methodology are discussed. It is shown that text analysis software is constrained not only by its functions, but also by its underlying theoretical assumptions. The paper offers recommendations for good practice in software commercialisation and application, stressing the importance of transparency and acknowledgement of biases.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Student Research Workshop associated with RANLP 2015 |
| Publication status | Published (VoR) - 2015 |