More Like this

1. The Interaction between Political Typology and Filter Bubbles in News Recommendation Algorithms

   https://doi.org/10.1145/3442381.3450113  

   Liu, Ping; Shivaram, Karthik; Culotta, Aron; Shapiro, Matthew A.; Bilgic, Mustafa (April 2021, WWW '21: Proceedings of the Web Conference 2021)

   null (Ed.)

   Algorithmic personalization of news and social media content aims to improve user experience; however, there is evidence that this filtering can have the unintended side effect of creating homogeneous "filter bubbles," in which users are over-exposed to ideas that conform with their preexisting perceptions and beliefs. In this paper, we investigate this phenomenon in the context of political news recommendation algorithms, which have important implications for civil discourse. We first collect and curate a collection of over 900K news articles from 41 sources annotated by topic and partisan lean. We then conduct simulation studies to investigate how different algorithmic strategies affect filter bubble formation. Drawing on Pew studies of political typologies, we identify heterogeneous effects based on the user's pre-existing preferences. For example, we find that i) users with more extreme preferences are shown less diverse content but have higher click-through rates than users with less extreme preferences, ii) content-based and collaborative-filtering recommenders result in markedly different filter bubbles, and iii) when users have divergent views on different topics, recommenders tend to have a homogenization effect. 

   more » « less
2. Two Computational Models for Analyzing Political Attention in Social Media

   Hemphill, L.; Schöpke-Gonzalez, A. M. (January 2020, Proceedings of the Fourteenth International AAAI Conference on Web and Social Media)

   Understanding how political attention is divided and over what subjects is crucial for research on areas such as agenda setting, framing, and political rhetoric. Existing methods for measuring attention, such as manual labeling according to established codebooks, are expensive and can be restrictive. We describe two computational models that automatically distinguish topics in politicians' social media content. Our models---one supervised classifier and one unsupervised topic model---provide different benefits. The supervised classifier reduces the labor required to classify content according to pre-determined topic list. However, tweets do more than communicate policy positions. Our unsupervised model uncovers both political topics and other Twitter uses (e.g., constituent service). These models are effective, inexpensive computational tools for political communication and social media research. We demonstrate their utility and discuss the different analyses they afford by applying both models to the tweets posted by members of the 115th U.S. Congress. 

   more » « less
3. Extracting Topics with Focused Communities for Social Content Recommendation

   https://doi.org/10.1145/2998181.2998259  

   Georgiou, Theodore; El Abbadi, Amr; Yan, Xifeng (February 2017, Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing)

   A thorough understanding of social media discussions and the demographics of the users involved in these discussions has become critical for many applications like business or political analysis. Such an understanding and its ramifications on the real world can be enabled through the automatic summarization of Social Media. Trending topics are offered as a high level content recommendation system where users are suggested to view related content if they deem the displayed topics interesting. However, identifying the characteristics of the users focused on each topic can boost the importance even for topics that might not be popular or bursty. We define a way to characterize groups of users that are focused in such topics and propose an efficient and accurate algorithm to extract such communities. Through qualitative and quantitative experimentation we observe that topics with a strong community focus are interesting and more likely to catch the attention of users. 

   more » « less
4. Percolation-based topic modeling for tweets

   Churchill, R.; Singh, L. (August 2020, WISDOM 2020 : The 9th KDD Workshop on Issues of Sentiment Discovery and Opinion Mining)

   This paper investigates topic modeling within a noisy domain. The goal is to generate topics that maximize topic coherence while introducing only a small amount of noise. The problem is motivated by the practical setting of short, noisy tweets, where it is important to generate topics containing a larger number of content words than noise words. For the most general version of this problem, we propose a new method, λ-CLIQ. It is a simple variant of the kclique percolation algorithm that employs for quasi-cliques during graph decomposition and percolation based on λ, a graph property variant. While the topics generated using our base algorithm are highly coherent, they are often contain too few words. To increase topic size, we add a post processing step that augments identified topic words using locally trained embeddings. We show that both λ-CLIQ and λ-CLIQ+ outperform the state of the art in terms of topic coherence on three distinct Twitter data sets. 

   more » « less
5. KHAN: Knowledge-Aware Hierarchical Attention Networks for Accurate Political Stance Prediction

   https://doi.org/10.1145/3543507.3583300  

   Ko, Yunyong; Ryu, Seongeun; Han, Soeun; Jeon, Youngseung; Kim, Jaehoon; Park, Sohyun; Han, Kyungsik; Tong, Hanghang; Kim, Sang-Wook (April 2023, WWW '23: Proceedings of the ACM Web Conference 2023)

   The political stance prediction for news articles has been widely studied to mitigate the echo chamber effect – people fall into their thoughts and reinforce their pre-existing beliefs. The previous works for the political stance problem focus on (1) identifying political factors that could reflect the political stance of a news article and (2) capturing those factors effectively. Despite their empirical successes, they are not sufficiently justified in terms of how effective their identified factors are in the political stance prediction. Motivated by this, in this work, we conduct a user study to investigate important factors in political stance prediction, and observe that the context and tone of a news article (implicit) and external knowledge for real-world entities appearing in the article (explicit) are important in determining its political stance. Based on this observation, we propose a novel knowledge-aware approach to political stance prediction (KHAN), employing (1) hierarchical attention networks (HAN) to learn the relationships among words and sentences in three different levels and (2) knowledge encoding (KE) to incorporate external knowledge for real-world entities into the process of political stance prediction. Also, to take into account the subtle and important difference between opposite political stances, we build two independent political knowledge graphs (KG) (i.e., KG-lib and KG-con) by ourselves and learn to fuse the different political knowledge. Through extensive evaluations on three real-world datasets, we demonstrate the superiority of KHAN in terms of (1) accuracy, (2) efficiency, and (3) effectiveness. 

   more » « less