Staying Informed: Supervised and Semi-Supervised Multi-View Topical Analysis of Ideological Perspective

Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 1140–1150, MIT, Massachusetts, USA, 9-11 October 2010. c⃝2010 Association for Computational Linguistics Staying Informed: Supervised and Semi-Supervised Multi-view Topical Analysis of Ideological Perspective Amr Ahmed School of Computer Science Carnegie Mellon University amahmed@cs.cmu.edu Eric P. Xing School of Computer Science Carnegie Mellon University epxing@cs.cmu.edu Abstract With the proliferation of user-generated arti- cles over the web, it becomes imperative to de- velop automated methods that are aware of the ideological-bias implicit in a document col- lection. While there exist methods that can classify the ideological bias of a given docu- ment, little has been done toward understand- ing the nature of this bias on a topical-level. In this paper we address the problem of modeling ideological perspective on a topical level using a factored topic model. We develop efficient inference algorithms using Collapsed Gibbs sampling for posterior inference, and give var- ious evaluations and illustrations of the util- ity of our model on various document collec- tions with promising results. Finally we give a Metropolis-Hasting inference algorithm for a semi-supervised extension with decent results. 1 Introduction With the avalanche of user-generated articles over the web, it is quite important to develop models that can recognize the ideological bias behind a given document, summarize where this bias is manifested on a topical level, and provide the user with alter- nate views that would help him/her staying informed about different perspectives. In this paper, we fol- low the notion of ideology as defines by Van Dijk in (Dijk, 1998) as “a set of general abstract beliefs commonly shared by a group of people.” In other words, an ideology is a set of ideas that directs one’s goals, expectations, and actions. For instance, free- dom of choice is a general aim that directs the ac- tions of“liberals”, whereas conservation of values is the parallel for “conservatives”. We can attribute the lexical variations of the word content of a document to three factors: • Writer Ideological Belief. A liberal writer might use words like freedom and choice re- gardless of the topical content of the document. These words define the abstract notion of be- lief held by the writer and its frequency in the document largely depends on the writer’s style. • Topical Content. This constitutes the main source of the lexical variations in a given docu- ment. For instance, a document about abortion is more likely to have facts related to abortion, health, marriage and relationships. • Topic-Ideology Interaction. When a liberal thinker writes about abortion, his/her abstract beliefs are materialized into a set of concrete opinions and stances, therefore, we might find words like: pro-choice and feminism. On the contrary, a conservative writer might stress is- sues like pro-life, God and faith. Given a collection of ideologically-labeled docu- ments, our goal is to develop a computer model that factors the document collection into a representation that reflects the aforementioned three sources of lex- ical variations. This representation can then be …

Content truncated to 500 words