Wouter Van Atteveldt

Wouter Van Atteveldt
Vrije Universiteit Amsterdam | VU · Department of Communication Science

PhD

About

68
Publications
57,716
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,099
Citations
Additional affiliations
February 2004 - present
Vrije Universiteit Amsterdam
Position
  • Professor

Publications

Publications (68)
Article
Full-text available
Growing concern about the democratic impact of automatically curated news platforms urges us to reconsider how such platforms should be designed. We propose a theoretical framework for personalised diversity nudges that can stimulate diverse news consumption on the individual level. To examine potential benefits and limitations of existing diversit...
Article
Most common methods for automatic text analysis in communication science ignore syntactic information, focusing on the occurrence and co-occurrence of individual words, and sometimes n-grams. This is remarkably effective for some purposes, but poses a limitation for fine-grained analyses into semantic relations such as who does what to whom and acc...
Preprint
The digital traces that people leave through their use of various online platforms provide tremendous opportunities for studying human behavior. However, the collection of these data is hampered by legal, ethical and technical challenges. We present a framework and tool for collecting these data through a data donation platform where consenting par...
Article
This article provides a model for how communication phenomena can be normativelyassessed using multiple normative perspectives simultaneously. We exemplify the proce-dure of multiperspectival normative assessment (MNA) using mediated reactions to ter-rorism as our case in point. We first identify the normative challenges related to thespeed and sub...
Article
Full-text available
Digital archives that document real-world events provide new opportunities for large-scale analyses of how news coverage represents reality. We present a method and open-source tool for linking event data to news articles, and demonstrate its application with an analysis of event and country level predictors of terrorism coverage in The Guardian fr...
Preprint
Full-text available
Growing concern about the democratic impact of automatically curated news platforms urges us to reconsider how such platforms should be designed. We propose a theoretical framework for personalised diversity nudges that can stimulate diverse news consumption on the individual level. To examine potential benefits and limitations of existing diversit...
Article
We examined the validity of 37 sentiment scores based on dictionary-based methods using a large news corpus and demonstrated the risk of generating a spectrum of results with different levels of statistical significance by presenting an analysis of relationships between news sentiment and U.S. presidential approval. We summarize our findings into f...
Article
Full-text available
Sentiment is central to many studies of communication science, from negativity and polarization in political communication to analyzing product reviews and social media comments in other sub-fields. This study provides an exhaustive comparison of sentiment analysis methods, using a validation set of Dutch economic headlines to compare the performan...
Article
Full-text available
News diversity in the media has for a long time been a foundational and uncontested basis for ensuring that the communicative needs of individuals and society at large are met. Today, people increasingly rely on online content and recommender systems to consume information challenging the traditional concept of news diversity. In addition, the very...
Preprint
Full-text available
We examined the validity of 37 sentiment scores based on dictionary-based methods using a large news corpus and demonstrated the risk of generating a spectrum of results with different levels of statistical significance by presenting an analysis of relationships between news sentiment and U.S. presidential approval. We summarize our findings into f...
Article
Full-text available
With global media content databases and online content being available, analyzing topical structures in different languages simultaneously has become an urgent computational task. Some previous studies have analyzed topics in a multilingual corpus by translating all items into a single language using a machine translation service, such as Google Tr...
Article
Full-text available
This study looks into how the combination of Islam, refugees, and terrorism topics leads to text-internal changes in the emotional tone of news articles and how these vary across countries and media outlets. Using a multilingual human-validated sentiment analysis, we compare fear and pity in more than 560,000 articles from the most important online...
Article
Full-text available
How to study media diversity has become a major concern in today’s media landscape. Many expect that algorithmic filtering and a shift of audiences from legacy media to new intermediaries decrease the diversity of news diets, leading to fragmented societies, polarization and spread of misinformation. Different fields, from journalism research to la...
Article
Full-text available
Open science and effective collaboration both require the sharing of data between researchers. This is especially true for computational methods, as the technical complexity and heterogeneous data sources often require collaboration between researchers in different institutions and jurisdictions. Many data sources, however, cannot be shared openly...
Article
Full-text available
Changes in political perceptions and preferences may result from the combined effects of news from various media. Estimating these combined effects requires the best possible, albeit different, measures of news obtained from self-selected mass media and social media that can be linked to panel survey data concerning perceptions and preferences. For...
Article
Computational Communication Research (CCR) is a new open access journal dedicated to publishing high quality computational research in communication science. This editorial introduction describes the role that we envision for the journal. First, we explain what computational communication science is and why a new journal is needed for this subfield...
Article
Full-text available
This article reviews the opportunities and challenges for computational research methods in the field of communication. Among the social sciences, communication stands out as a discipline with a relatively low-profile institutionalized focus on the in-house development of methods. Computational tools are changing this, and they are catalyzing a new...
Article
Full-text available
Computational communication science (CCS) offers an opportunity to accelerate the scope and pace of discovery in communication research. This article argues that CCS will profit from adopting open science practices by fostering the reusability of data and code. We discuss the goals and challenges related to creating reusable data and code and offer...
Article
A crucial challenge in measuring how text represents an entity is the need to associate each representative expression with a relevant entity to generate meaningful results. Common solutions to this problem are usually based on proximity methods that require a large corpus to reach reasonable levels of accuracy. We show how such methods for the ass...
Article
Issues are not neutral. This study about the Dutch 2016 referendum on the EU–Ukraine association treaty asks which issues dominated the news media in the campaign, how the news about these issues influenced the saliency of benefits and disadvantages of the treaty, and how the latter in turn influenced turnout and the vote. A content analysis of new...
Article
Full-text available
The recent increase in digitally available data, tools, and processing power is fostering the use of computational methods to the study of communication. This special issue discusses the validity of using big data in communication science and showcases a number of new methods and applications in the fields of text and network analysis. Computationa...
Conference Paper
Full-text available
Research from communication science has shown that stereotypical ideas are often reflected in language use. Media coverage of different groups in society influences the perception people have about these groups and even increases distrust and polarization among different groups. Investigating the forms of (especially subtle) stereotyping can raise...
Article
Full-text available
Computational text analysis has become an exciting research field with many applications in communication research. It can be a difficult method to apply, however, because it requires knowledge of various techniques, and the software required to perform most of these techniques is not readily available in common statistical software packages. In th...
Chapter
Full-text available
Organizations from the same industry or field often tend to become more similar over time, despite being different in terms of for example strategies, goals, or performance. However, recently scholars pointed out that organizational fields are dynamic entities with permeable boundaries, thus indicating that prior literature may have oversimplified...
Article
This article presents a new method and open source R package that uses syntactic information to automatically extract source–subject–predicate clauses. This improves on frequency based text analysis methods by dividing text into predicates with an identified subject and optional source, extracting the statements and actions of (political) actors as...
Article
Full-text available
This paper investigates the influence of news agency Algemeen Nederlands Persbureau (ANP) on the coverage and diversity of political news in Dutch national newspapers. Using computational text analysis, we analyzed the influence on print newspapers across three years (1996, 2008, and 2013) and compared influence on print and online newspapers in 20...
Article
Full-text available
The European elections in 2014 were the first to be held after a long period in which EU-related news was prominent in the media. They were held after years of daily news about the euro crisis and after months of news about the popular uprising in the Ukraine against president Yanukovych, who had refused to sign the association agreement with the E...
Article
Between 2007 and 2011, the number of registered juvenile suspects declined by 44% but the Dutch public did not feel any safer. In this research we study media coverage of youth crime and interview journalists and their sources, in order to investigate the relationship between journalists, their sources and the possible effects on the public with re...
Article
Full-text available
The huge collections of news content which have become available through digital technologies both enable and warrant scientific inquiry, challenging journalism scholars to analyse unprecedented amounts of texts. We propose Latent Dirichlet Allocation (LDA) topic modelling as a tool to face this challenge. LDA is a cutting edge technique for conten...
Article
Full-text available
On newspaper websites, journalists can observe the preferences of the audience in unprecedented detail and for low costs, based on the audience clicks (i.e. page views) for specific news articles. This article addresses whether journalists use this information to cater to audience preferences in their news selection choices. We analyzed the print a...
Article
Full-text available
The prominence of party leaders in the media is one of the presumed causes of leader effects (i.e., the influence of party leader evaluation on the voting decision). Yet there is scant knowledge of the relationship between attention for party leaders in the news and the weight of party leader evaluations in the voting decision. This study fills thi...
Article
Full-text available
Although diverse political news has been recognized as a requirement for a well-functioning democracy, longitudinal research into this topic is sparse. In this article, we analyse the development of diversity in election coverage in the Netherlands between 1994 and 2012. We distinguish between diversity for party and issue coverage, and look at dif...
Article
Full-text available
This paper applies the homophily thesis to public diplomacy and offers an empirical examination of a country’s success in its mediated public diplomacy efforts. It analyzes international frame building, the process of creating or changing media frames in the international communications arena, by applying it to the case of Israeli mediated public d...
Chapter
Full-text available
If humans are political animals, and language is their most versatile communication tool, then the old question what should be extracted from political texts to understand politics deserves renewed attention. Recent advances in the information and communication sciences have resulted in new means to process political texts, especially advances in t...
Article
Full-text available
The media logic thesis holds that the content of political news is the product of news values and format requirements that media make use of to attract news consumers. This study tests whether three content characteristics – personalized, contest and negative coverage – manifest a single media logic by analysing whether they co-vary over time. It a...
Article
Full-text available
Social scientists have long hand-labeled texts to create datasets useful for studying topics from congressional policymaking to media reporting. Many social scientists have begun to incorporate machine learning into their toolkits. RTextTools was designed to make machine learning accessible by providing a start-to-finish product in less than 10 ste...
Article
Full-text available
Content analysis of media framing is difficult to do using keyword or dictionary approaches. This paper presents an automatic Semantic Network Analysis method for extracting framing. This method consists of four steps. (1) Sentences are analysed syntactically; (2) Semantic relations are extracted from the syntactic structure; (3) actors and issues...
Article
Full-text available
Whether financial news may contribute to market panics is not an innocent question. A positive answer is easily used as a legitimation to limit the freedom of financial journalists. Long-term effects of news are moreover inconsistent with the Efficient Market Hypothesis (EMH), which maintains that new information gives immediately rise to a new equ...
Article
Full-text available
This paper contributes to the analysis of the interplay of public relations and news in crisis situations, and the conceptualization of strategic framing by introducing the idea of associative frames and the method of semantic network analysis to the PR research field. By building on a more advanced understanding of communication as process of soci...
Article
Full-text available
Analysis of political communication is an important aspect of political research. Thematic content analysis has yielded considerable success both with manual and automatic coding, but Semantic Network Analysis has proven more difficult, both for humans and for the computer. This article presents a system for an automated Semantic Network Analysis o...
Conference Paper
Full-text available
For some years now ontologies have been used in Social Science, e.g., in annotation of newspaper articles for disambiguating concepts within Media Analysis. These ontologies and annotations have now become objects of study in their own right, as they implicitly represent the shift of meaning of political concept over time. Manual mappings, which ar...
Article
Since 1995 the techniques and capacities to store new electronic data and to make it available to many persons have become a common good. As of then, different organizations, such as research institutes, universities, libraries, and private companies (Google) started to scan older documents and make them electronically available as well. This has g...
Article
The distribution of topic attention is an essential part in the political agenda setting literature. Which policy problem gets priority and when? The American datasets of the policy agendas projects (Washington and PennState University) consists of thousands of topic coded documents, such as Bills, State of the Union speeches, and articles from the...
Article
Full-text available
Many research questions in political communication can be answered by representing text as a network of positive or negative relations between actors and issues such as conducted by semantic network analysis. This article presents a system for automatically determining the polarity (positivity/negativity) of these relations by using techniques from...
Article
Full-text available
The 9/11 terrorist attacks and later attacks such as those in London and Madrid shocked the world and found their way into the newspapers of many countries. The authors study the international coverage of these events in the context of globalization versus localization and the creation of the dominant post-cold war frame of the War on Terror. Using...
Conference Paper
Full-text available
The media play an important role in the functioning of our society. This role is extensively studied by Communication Scientists, requiring a systematic analysis of media content. The methods developed in this field utilize complex data models and background knowledge. This data is generally represented ad hoc, making it difficult to analyze, combi...
Conference Paper
Full-text available
To get a better understanding of the in∞uence of the media on current political events, researchers in Communication Science have recently reported on several case studies, in which they analyse certain patterns in newspaper articles, such as internal disagreement or criticism within a political party. In this paper we explain how Hybrid Logic can...
Article
Full-text available
Abstract Information Extraction can be conducted by assigning labels drawn from a large set to words or phrases. However, predicting the labels of un seen examples using such a large set of labels poses a number,of challenges. Using a Maximum,Entropy Markov Model with features that generalise over labels, it was shown that a significant improvement...
Article
Full-text available
Prior research on the L1 acquisition of English suggests that long after children have acquired knowledge of the basic syntax of who questions they nonetheless have greater difficulty accessing or using this knowledge in the case of object who questions (O-WH) such as (1b) than in the case of subject who questions (S-WH) such as (1a)...
Article
Full-text available
Prior research on L1 acquisition of English suggests that preschool children find it more difficult to process subject who questions (S-WH) such as (1a) than object who questions (O-WH) such as (1b), long after they have acquired the basic syntax of such questions. However, evidence from previous research in support of this asymmetry is by no means...
Article
Full-text available
Increasing numbers of high quality tools and data sets are becoming available for the study of media content, providing an opportu-nity for more rapid progress in Communication Science if these tools and data sets could be effectively combined and shared. In order to do so, it would be beneficial to have a shared Data format that is flexible enough...
Article
Full-text available
A frequent motivation for annotating documents using ontologies is to allow more e-cient search. For collections of newspaper articles, it is often di-cult to flnd spe- ciflc articles based on keywords or topics alone. This paper describes a system that uses a formalisation of the content of newspaper articles to answer complex queries. The data fo...
Article
Full-text available
The images of the second plane flying into the World Trade Center on September 11th, 2001 shook the world and shaped the way terrorism would be reported on in the years afterwards. Analyzing all articles on terror in 4 newspapers in the US and UK from 1996 to 2006, we conducted an automated study of the way terrorism events were framed before and a...
Article
Full-text available
Many research questions in political communication can be answered by representing text as a network of positive or negative relations between actors and issues. This paper presents a system for automati- cally determining whether these relations are positive or negative by using techniques from Sentiment Analysis. We used a Machine Learning approa...