Promoting Civil Discourse Through Search Engine Diversity

Abstract

The ability of modern web services such as news aggregators and search engines to tailor their results to the tastes of individuals, together with people's preference for reading opinions which reinforce their own viewpoints, have raised concerns that people are nowadays exposed to a narrow range of view-points, a phenomenon referred to as the ''filter bubble''. In this paper we focus on increasing exposure to varied political opinions with a goal of improving civil discourse. We develop a method to algorithmically encourage people to read diverse political opinions and test it when people actively seek information. First, analyzing data from a popular search engine we show that people are indeed more likely to read opinions consistent with their own. Interestingly, they are more likely to read news from opposing sites when the language model of a particular news item is close to the language model of their own political leaning. Based on this finding, we describe a method for assisting people to read divergent opinions by choosing documents of opposing viewpoints that have a language model closer to their own language model. We test our method on a number of web searchers and show that pages of the opposing side which were more similar than the average persons' own language model tended to be clicked 38% more than those below. We also describe the long-term effects of our method, showing that people who were shown more diverse results continued reading more diverse results and overall became more interested in news.

Content Bias in Online Health Search

“…Biases in the presentation of results on personal and controversial topics have also been examined [Pariser 2011;Gamper 2011, 2013;Yom-Tov et al 2014]. Via functionality such as search personalization, search engines can filter available information to only that supportive of the searcher's position [Pariser 2011].…”

“…Via functionality such as search personalization, search engines can filter available information to only that supportive of the searcher's position [Pariser 2011]. Methods have been proposed to expose searchers to opposing perspectives [Yom-Tov et al 2014], to promote a balanced view on important issues and encourage civil discourse. Gamper [2011, 2013] seek to mine opinions on underrepresented perspectives in search results for subjective queries.…”

Utilising Wikipedia for Text Mining Applications

“…Despite the above-mentioned efforts together with efforts at search result diversification that aim to minimize the effects of controversial Web content [224], there still remains a need for a system that helps pursue a qualitative and quantitative analysis of the amount of bias and controversy within the search results. In the following subsection, we present an overview of a perspective-aware search engine that aims to support such analyses.…”

Context & Semantics in News & Web Search

“…For example, YomTov et al [232] algorithmically encourage people to read diverse political opinions by increasing their exposure to varied political opinions, with the goal of improving civil discourse. For this, they consider web search queries that are clearly associated with a certain political stance (e.g., obamacare or tea party).…”