Predicting Response to Political Blog Posts with Topic Models

Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the ACL, pages 477–485, Boulder, Colorado, June 2009. c⃝2009 Association for Computational Linguistics Predicting Response to Political Blog Posts with Topic Models Tae Yano William W. Cohen Noah A. Smith School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213, USA {taey,wcohen,nasmith}@cs.cmu.edu Abstract In this paper we model discussions in online political blogs. To do this, we extend Latent Dirichlet Allocation (Blei et al., 2003), in var- ious ways to capture different characteristics of the data. Our models jointly describe the generation of the primary documents (posts) as well as the authorship and, optionally, the contents of the blog community’s verbal reac- tions to each post (comments). We evaluate our model on a novel comment prediction task where the models are used to predict which blog users will leave comments on a given post. We also provide a qualitative discussion about what the models discover. 1 Introduction Web logging (blogging) and its social impact have recently attracted considerable public and scientific interest. One use of blogs is as a community dis- cussion forum, especially for political discussion and debate. Blogging has arguably opened a new channel for huge numbers of people to express their views with unprecedented speed and to unprece- dented audiences. Their collective behavior in the blogosphere has already been noted in the Ameri- can political arena (Adamic and Glance, 2005). In this paper we attempt to deliver a framework useful for analyzing text in blogs quantitatively as well as qualitatively. Better blog text analysis could lead to better automated recommendation, organization, ex- traction, and retrieval systems, and might facilitate data-driven research in the social sciences. Apart from the potential social utility of text pro- cessing for this domain, we believe blog data is wor- thy of scientific study in its own right. The sponta- neous, reactive, and informal nature of the language in this domain seems to defy conventional analytical approaches in NLP such as supervised text classifi- cation (Mullen and Malouf, 2006), yet the data are rich in argumentative, topical, and temporal struc- ture that can perhaps be modeled computationally. We are especially interested in the semi-causal struc- ture of blog discussions, in which a post “spawns” comments (or fails to do so), which meander among topics and asides and show the personality of the participants and the community. Our approach is to develop probabilistic mod- els for the generation of blog posts and comments jointly within a blog site. The model is an extension of Latent Dirichlet Allocation (Blei et al., 2003). Unsupervised topic models can be applied to collec- tions of unannotated documents, requiring very lit- tle corpus engineering. They can be easily adapted to new problems by altering the graphical model, then applying standard probabilistic inference algo- rithms. Different models can be compared to ex- plore the ramifications of different hypotheses about the data. For example, we will explore whether the contents of posts a user has commented on in …

Content truncated to 500 words