Search for: All records

Headlines play an important role in both news audiences' attention decisions online and in news organizations’ efforts to attract that attention. A large body of research focuses on developing generally applicable heuristics for more effective headline writing. In this work, we measure the importance of a number of theoretically motivated textual features to headline performance. Using a corpus of hundreds of thousands of headline A/B tests run by hundreds of news publishers, we develop and evaluate a machine-learned model to predict headline testing outcomes. We find that the model exhibits modest performance above baseline and further estimate an empirical upper bound for such content-based prediction in this domain, indicating an important role for non-content-based factors in test outcomes. Together, these results suggest that any particular headline writing approach has only a marginal impact, and that understanding reader behavior and headline context are key to predicting news attention decisions. 

This article explores how Twitter’s algorithmic timeline influences exposure to different types of external media. We use an agent-based testing method to compare chronological timelines and algorithmic timelines for a group of Twitter agents that emulated real-world archetypal users. We first find that algorithmic timelines exposed agents to external links at roughly half the rate of chronological timelines. Despite the reduced exposure, the proportional makeup of external links remained fairly stable in terms of source categories (major news brands, local news, new media, etc.). Notably, however, algorithmic timelines slightly increased the proportion of “junk news” websites in the external link exposures. While our descriptive evidence does not fully exonerate Twitter’s algorithm, it does characterize the algorithm as playing a fairly minor, supporting role in shifting media exposure for end users, especially considering upstream factors that create the algorithm’s input—factors such as human behavior, platform incentives, and content moderation. We conclude by contextualizing the algorithm within a complex system consisting of many factors that deserve future research attention. 

Social media platforms have increasingly become an important way for news organizations to distribute content to their audiences. As news organizations relinquish control over distribution, they may feel the need to optimize their content to align with platform logics to ensure economic sustainability. However, the opaque and often proprietary nature of platform algorithms makes it hard for news organizations to truly know what kinds of content are preferred and will perform well. Invoking the concept of algorithmic ‘folk theories,’ this article presents a study of in-depth, semi-structured interviews with 18 U.S.-based news journalists and editors to understand how they make sense of social media algorithms, and to what extent this influences editorial decision making. Our findings suggest that while journalists’ understandings of platform algorithms create new considerations for gatekeeping practices, the extent to which it influences those practices is often negotiated against traditional journalistic conceptions of newsworthiness and journalistic autonomy. 

This work presents an audit study of Apple News as a sociotechnical news curation system that exercises gatekeeping power in the media. We examine the mechanisms behind Apple News as well as the content presented in the app, outlining the social, political, and economic implications of both aspects. We focus on the Trending Stories section, which is algorithmically curated, and the Top Stories section, which is human-curated. Results from a crowdsourced audit showed minimal content personalization in the Trending Stories section, and a sock-puppet audit showed no location-based content adaptation. Finally, we perform an extended two-month data collection to compare the human-curated Top Stories section with the algorithmically-curated Trending Stories section. Within these two sections, human curation outperformed algorithmic curation in several measures of source diversity, concentration, and evenness. Furthermore, algorithmic curation featured more “soft news” about celebrities and entertainment, while editorial curation featured more news about policy and international events. To our knowledge, this study provides the first data-backed characterization of Apple News in the United States. 

This research shows that members of different ideological groups in the United States can use different search terms when looking for information about political candidates, but that difference is not enough to yield divergent search results on Google. Search engines are central in information seeking during elections, and have important implications for the distribution of information and, by extension, for democratic society. Using a method involving surveys, qualitative coding, and quantitative analysis of search terms and search results, we show that the sources of information that are returned by Google for both liberal and conservative search terms are strongly correlated. We collected search terms from people with different ideological positions about Senate candidates in the 2018 midterm election from the two main parties in the U.S., in three large and politically distinct states: California, Ohio, and Texas. We then used those search terms to scrape web results and analyze them. Our analysis shows that, in terms of the differences arising from individual search term choices, Google results exhibit a mainstreaming effect that partially neutralizes differentiation of search behaviors, by providing a set of common results, even to dissimilar searches. Based on this analysis, this article offers two main contributions: first, in the development of a method for determining group-level differences based on search input bias; and second, in demonstrating how search engines respond to diverse information seeking behavior and whether that may have implications for public discourse. 

Smart speakers are becoming ubiquitous in daily life. The widespread and increasing use of smart speakers for news and information in society presents new questions related to the quality, source diversity and credibility, and reliability of algorithmic intermediaries for news consumption. While user adoption rates soar, audit instruments for assessing information quality in smart speakers are lagging. As an initial effort, we present a conceptual framework and data-driven approach for evaluating smart speakers for information quality. We demonstrate the application of our framework on the Amazon Alexa voice assistant and identify key information provenance and source credibility problems as well as systematic differences in the quality of responses about hard and soft news. Our study has broad implications for news media and society, content production, and information quality assessment. 

This paper presents an algorithm audit of the Google Top Stories box, a prominent component of search engine results and powerful driver of traffic to news publishers. As such, it is important in shaping user attention towards news outlets and topics. By analyzing the number of appearances of news article links we contribute a series of novel analyses that provide an in-depth characterization of news source diversity and its implications for attention via Google search. We present results indicating a considerable degree of source concentration (with variation among search terms), a slight exaggeration in the ideological skew of news in comparison to a baseline, and a quantification of how the presentation of items translates into traffic and attention for publishers. We contribute insights that underscore the power that Google wields in exposing users to diverse news information, and raise important questions and opportunities for future work on algorithmic news curation. 

Audience analytics are an increasingly essential part of the modern newsroom as publishers seek to maximize the reach and commercial potential of their content. On top of a wealth of audience data collected, algorithmic approaches can then be applied with an eye towards predicting and optimizing the performance of content based on historical patterns. This work focuses specifically on content optimization practices surrounding the use of A/B headline testing in newsrooms. Using such approaches, digital newsrooms might audience-test as many as a dozen headlines per article, collecting data that allows an optimization algorithm to converge on the headline that is best with respect to some metric, such as the click-through rate. This article presents the results of an interview study which illuminate the ways in which A/B testing algorithms are changing workflow and headline writing practices, as well as the social dynamics shaping this process and its implementation within US newsrooms.