Why is That a Background Article: A Qualitative Analysis of Relevance for News Background Linking

Abstract

News background linking is the problem of finding online resources that can provide valuable context and background information to help the reader comprehend a given news article. While the problem has recently attracted several researchers, however, the notion of background relevance is not well-studied and it requires better understanding to ensure effective system performance. In this paper, we conduct a qualitative analysis on a sample of 25 query news articles and 152 of their corresponding background articles, in addition to 50 of non-background ones. The goal of the study is to shed some light on the relationship between the query articles and the background articles, and provide informative insights for developing more effective background retrieval models. For instance, our analysis shows that event-driven query articles are, on average, harder to process than others, hence they should be handled differently. It also shows that discussing subtopics in detail and adding new informative topics are both essential factors for highly-relevant background articles. Moreover, it shows that a high lexical similarity between a query article and a background one is neither sufficient nor necessary.