Targeted Topic Modeling for Focused Analysis
Shuai Wang*, University of Illinois at Chicago; Zhiyuan Chen, UIC; Geli Fei, Univ of Illinois at Chicago; Bing Liu, Univ of Illinois at Chicago; Sherry Emery, University of Illinois at Chicago
One of the overarching tasks of document analysis is to ﬁnd what topics people talk about. One of the main techniques for this purpose is topic modeling. So far many models have been proposed. However, the existing models typically per-form full analysis on the whole data to ﬁnd all topics. This is certainly useful, but in practice we found that the user almost always also wants to perform more detailed analyses on some speciﬁc aspects, which we refer to as targets (or targeted aspects). Current full-analysis models are not suitable for such analyses as their generated topics are often too coarse and may not even be on target. For example, given a set of tweets about e-cigarette, one may want to ﬁnd out what topics under discussion are speciﬁcally related to children. Likewise, given a collection of online reviews about a camera, a consumer or camera manufacturer may be interested in ﬁnding out all topics about the camera’s screen, the targeted aspect. As we will see in our experiments, current full topic models are ineﬀective for such targeted analyses. This paper studies this problem and proposes a novel targeted topic model (TTM) to enable focused analyses on any speciﬁc aspect of interest. Our experimental results demonstrate the eﬀectiveness of the TTM.
Filed under: Dimensionality Reduction