Visualization of the Topic Space of Argument Search Results in args.me

Abstract

In times of fake news and alternative facts, pro and con arguments on controversial topics are of increasing importance. Recently, we presented args.me as the first search engine for arguments on the web. In its initial version, args.me ranked arguments solely by their relevance to a topic queried for, making it hard to learn about the diverse topical aspects covered by the search results. To tackle this shortcoming, we integrated a visualization interface for result exploration in args.me that provides an instant overview of the main aspects in a barycentric coordinate system. This topic space is generated ad-hoc from controversial issues on Wikipedia and argumentspecific LDA models. In two case studies, we demonstrate how individual arguments can be found easily through interactions with the visualization, such as highlighting and filtering.

Viewpoint Diversity in Search Results

“…Recent work has already applied automatic stance detection methods to search results [22] but did so far not attempt to identify logics of evaluation. However, once such automatic systems have become more comprehensive, researchers and practitioners could easily combine them with existing methods for extracting arguments [12,60] and visualize viewpoints [4,17] in search results.…”

Using Information-Seeking Argument Mining to Improve Service

“…Even if the arguments are ranked, going through a potentially long list of results can still be cumbersome. Therefore, IS-AM usually summarizes all pro arguments into clusters containing similar arguments (Ajjour et al, 2018; Bar-Haim et al, 2020) using, for example, agglomerative hierarchical clustering, such as using the average linkage criterion. Such clustering builds on a pairwise similarity (Reimers et al, 2019).…”

The Meant, the Said, and the Understood: Conversational Argument Search and Cognitive Biases

“…2 A major challenge of conversational argument search systems is summarizing the pros and cons for a quick overview [16] (recall Figure 2). One approach is to visualize the distribution of arguments according to certain aspects, such as the argument's topics [1]. Other possible aspects could be the argument's moral sentiment [17], the facets examined in comparative arguments [26], or the types of evidence given [23].…”