We got a new project – SHARENEWS! We are happy to announce that we got funding (and data access) to conduct a multi-national project on the shareworthiness of news on Facebook. The multi-national project is coordinated by a PI from ccs.amsterdam, Damian Trilling; and also Judith Möller, Wouter van Atteveldt, and Claes de Vreese are part of the Amsterdam team. See here for the whole team.
We are happy to share that a large number of our submissions for the upcoming conference of the International Communication Association (ICA 2019) were accepted.
Gathering Mobile News Consumption Traces: An Overview of Possibilities and a Prototype Tool based on Google Takeout
Wouter van Atteveldt, Laurens Bogaardt, Vincent van Hees, Felicia Loecherbach, Judith Moeller, Damian Trilling
This paper gives an overview of technical, legal, and ethical possibilities and challenges in collecting digital trace data of mobile news consumption. The shift to online and especially mobile news consumption has led to the creation of unprecedented amounts of data on individual news consumption behavior. In theory, we can now know which respondents viewed (and liked, shared, and commented on) which news articles at which time. This allows a much more fine-grained study of media effects compared to the ‘classical’ method of linking media content to (panel) survey data. In this paper, we first discuss the criteria and desirable aspects for a possible solution. We then present an overview of different possibilities and discuss the extent to which each solution meets the listed criteria. Based on this discussion, we then present a prototype for using the activity log download or ‘takeout’ functionality offered by modern platforms to construct a similar system to the Web Historian discussed above.
It takes three to tango: The interplay of political press releases, social media and newspapers
Felicia Loecherbach, Damian Trilling
If a party wants to communicate issues, it issues a press release which gets picked up by the media and distributed to the audience. This “tango” of politics and media might have been altered over the past decade by the advent of a third partner: social media. In this study we determine whether signs of substitution of press releases by social media activity can be seen over time, indicating a change in the communication channels used by political parties. Second, we look at the influence of press releases on press coverage to determine to which extent the former exhibits influence on the latter. This sheds the light on the development of press releases’ agenda setting function and power to influence the public discourse via media outlets. Time series analysis and similarity calculations are applied to datasets including party communications (press releases, Facebook posts) and media content of the past decade.
3bij3 – A framework for testing effects of recommender systems on news exposure
Felicia Loecherbach, Damian Trilling
The impact of recommender systems on how we consume and perceive news is still understudied. To shed more light on this, we developed one of the first software solutions for such studies, and present 3bij3. It consists of a news application interface for study participants that displays a 3×3 grid of the nine most relevant news articles to a user, selected by different mechanisms (e.g., explicit customization vs based on past behavior). Compared to previous work, 3bij3 gives researchers control over the recommendation system under study and creates a realistic environment for the participants. It integrates web scraping/parsing, supervised machine learning for labeling articles, different recommender systems, a web interface for participants, and gamification elements (earning points for interaction). 3bij3 can be used to conduct large-scale field experiments, in which participants’ use of the site can be tracked over extended periods of time.
Finding your way: How news consumers seek and find news about different topics on online platforms
The complexity and diversity of today’s media landscape provides many challenges for scholars studying online news consumption. Yet it is unclear how news consumers navigate the wealth of online news. To move forward, we used a custom-built system–passively tracking online news consumers 24/7–to examine how context (i.e., platform) and content (i.e., news topic) features affect patterns of online news consumption. This bottom-up design resulted in a large data set containing more than 1 million news-related Web pages, from 165 different news websites, as well as search engines and social media, collected over 8 months in 2017/18. We found that news consumers often directly visit the homepage of their favorite (typically mainstream) news outlet, and continue browsing within that same news outlet. Our findings also show a strong preference for entertainment news over any other topic. Social media frequently expose users to entertainment news, but are not necessarily the starting point to this type of news.
Guilty by Association: Using Word Embeddings to Measure Ethnic Stereotypes in News Coverage
Anne C. Kroon, Damian Trilling, Tamara Raats
The current study provides a new level of empirical evidence for the nature of ethnic stereotypes in news coverage by drawing on a sample of more than three million Dutch news items. The study’s findings demonstrate that universally-accepted dimensions of stereotype content (i.e., low-status and high-threat attributes) can be replicated in news media coverage across a diverse set of ingroup and outgroup categories. News representations of minorities have become progressively negative and remote from factual integration outcomes, and are therefore rather an artifact of news production processes than a true reflection of what is actually happening in society.
We are pleased to announce that we are hosting a workshop on the use of tracking data in communication science. By bringing together scholars from different institutions and countries, we hope to get insights into pitfalls and opportunities as well as best practices.
Felicia combines a strong communication science background with very good technical skills. She completed the UvA research master in Communication Science. For her thesis she implemented her own news recommender system and web interface in python for conducting live, large-scale experiments tracking usage over time. It combines web scraping, machine learning, different customization options as well as gamification elements to enable testing various forms of news personalization in a controlled, yet realistic environment.
In the filter bubbles project, she will concentrate on the substantive analysis of (mobile) digital traces of news consumption behaviour: what news are people actually exposed to and choose to consume, can we find substantial evidence for echo chambers or filter bubbles, and if so what are the possible consequences for political knowledge and attitudes? Her other research interests include the interplay between political public relations and (social) media as well as furthering the usage of computational methods in communication science. She contributes for example to the open-source project INCA to facilitate collection, processing and analysis of online (textual) data for social scientists.
We am very excited to announce that we just launched Computational Communication Research (CCR), a new open-access peer-reviewed journal dedicated to development and applications of computational methods for communication science. We hope that CCR will serve as central home for communication scientists with an interest in and focus on computational methods — a place to read and publish the cutting edge work in our growing subfield.
Please see the inaugural call for papers at http://computationalcommunication.org/inaugural-cfp/ (abstracts 30 Sept, manuscripts 30 Nov), and consider submitting your best computational work to the first issue!
Don’t hesitate to contact us for more information, and looking forward to your submissions!