human interpretation

Topic modeling helped discover candidate codes but could not replace human interpretation

Zhiqiang Cai, Amanda Siebert-Evenstone, Brendan Eagan, David Williamson Shaffer

2nd International Conference on Quantitative Ethnography (ICQE 2020)

Whether unsupervised topic models can support the discovery of qualitative codes in large textual corpora. Topics often mixed several human codes, and words linked to one human code could appear across multiple topics; concise topic-word lists were more useful as discovery aids than direct replacements for codes. Alignment with one coded corpus does not establish that a topic model will recover valid constructs in another domain, language, or preprocessing pipeline.

Проверенное резюме статьи пока доступно на английском языке.