"Draw My Topics": Find Desired Topics fast from large scale of Corpus
This provides a faster way for social scientists to find desired topics from large corpora, though it appears incremental as it builds on standard topic modeling methods.
The researchers tackled the problem of incorporating social scientists' interests into topic modeling by developing the 'Draw My Topics' toolkit, which uses a Vector Space Model and Conditional Entropy algorithm to connect user preferences with unsupervised topic models, demonstrating its application on the Diachronic People's Daily Corpus in Chinese.
We develop the "Draw My Topics" toolkit, which provides a fast way to incorporate social scientists' interest into standard topic modelling. Instead of using raw corpus with primitive processing as input, an algorithm based on Vector Space Model and Conditional Entropy are used to connect social scientists' willingness and unsupervised topic models' output. Space for users' adjustment on specific corpus of their interest is also accommodated. We demonstrate the toolkit's use on the Diachronic People's Daily Corpus in Chinese.