Aktuelle Publikationen

Background: Research has repeatedly shown that exposure to suicide-related news media content is associated with suicide rates, with some content characteristics likely having harmful and others potentially protective effects. Although good evidence exists for a few selected characteristics, systematic and large-scale investigations are lacking. Moreover, the growing importance of social media, particularly among young adults, calls for studies on the effects of the content posted on these platforms.
Objective: This study applies natural language processing and machine learning methods to classify large quantities of social media data according to characteristics identified as potentially harmful or beneficial in media effects research on suicide and prevention. Methods: We manually labeled 3202 English tweets using a novel annotation scheme that classifies suicide-related tweets into 12 categories. Based on these categories, we trained a benchmark of machine learning models for a multiclass and a binary classification task. As models, we included a majority classifier, an approach based on word frequency (term frequency-inverse document frequency with a linear support vector machine) and 2 state-of-the-art deep learning models (Bidirectional Encoder Representations from Transformers [BERT] and XLNet). The first task classified posts into 6 main content categories, which are particularly relevant for suicide prevention based on previous evidence. These included personal stories of either suicidal ideation and attempts or coping and recovery, calls for action intending to spread either problem awareness or prevention-related information, reporting of suicide cases, and other tweets irrelevant to these 5 categories. The second classification task was binary and separated posts in the 11 categories referring to actual suicide from posts in the off-topic category, which use suicide-related terms in another meaning or context.
Results: In both tasks, the performance of the 2 deep learning models was very similar and better than that of the majority or the word frequency classifier. BERT and XLNet reached accuracy scores above 73% on average across the 6 main categories in the test set and F1-scores between 0.69 and 0.85 for all but the suicidal ideation and attempts category (F1=0.55). In the binary classification task, they correctly labeled around 88% of the tweets as about suicide versus off-topic, with BERT achieving F1-scores of 0.93 and 0.74, respectively. These classification performances were similar to human performance in most cases and were comparable with state-of-the-art models on similar tasks.
Conclusions: The achieved performance scores highlight machine learning as a useful tool for media effects research on suicide. The clear advantage of BERT and XLNet suggests that there is crucial information about meaning in the context of words beyond mere word frequencies in tweets about suicide. By making data labeling more efficient, this work has enabled large-scale investigations on harmful and protective associations of social media content with suicide rates and help-seeking behavior.

What kind of welfare state do voters of populist radical right parties (PRRPs) want and how do their preferences differ from voters of mainstream left- and right-wing parties? In this paper, we draw on an original, representative survey of public opinion on education and related social policies in eight Western European countries to measure (1) support for social transfers, (2) support for workfare and (3) support for social investment. Challenging the view that PRRPs turned into pro-welfare parties, our results indicate that their voters want a particularistic-authoritarian welfare state, displaying moderate support only for ‘deserving’ benefit recipients (e.g. the elderly), while revealing strong support for a workfare approach and little support for social investment. These findings have important implications for contemporary debates about the future of capitalism and the welfare state.

Does endorsing an Islamist agenda protect a candidate involved in corruption from negative voter evaluations? The corruption literature suggests that voter reactions to corruption are not unbiased and as such Islamist agendas could potentially mitigate the negative effects of a corruption scandal, especially in religious societies. The political Islam literature suggests that endorsing an Islamist agenda would not shield corrupt politicians from negative reactions of the voters. We directly answer this question through 2 nationally representative survey experiments in the world’s most populous Muslim democracy Indonesia. Our findings are 2-fold. First, Islamist agendas, in general, have only little effects on voter support for a candidate. Second, voters punish corrupt candidates equally, regardless whether or not they endorse an Islamist agenda.

Measuring sentiment in social media text has become an important practice in studying emotions at the macroscopic level. However, this approach can suffer from methodological issues like sampling biases and measurement errors. To date, it has not been validated if social media sentiment can actually measure the temporal dynamics of mood and emotions aggregated at the level of communities. We ran a large-scale survey at an online newspaper to gather daily mood self-reports from its users, and compare these with aggregated results of sentiment analysis of user discussions. We find strong correlations between text analysis results and levels of self-reported mood, as well as between inter-day changes of both measurements. We replicate these results using sentiment data from Twitter. We show that a combination of supervised text analysis methods based on novel deep learning architectures and unsupervised dictionary-based methods have high agreement with the time series of aggregated mood measured with self-reports. Our findings indicate that macro level dynamics of mood expressed on an online platform can be tracked with social media text, especially in situations of high mood variability.

Autocratic governments routinely interfere in digital communication technology for political purposes. However, citizens can use different technologies to bypass government interference. This article examines how political protest influences the use of anonymity-preserving digital services in autocracies. Citizens should be more likely to use these tools during high political tension because they fear governmental surveillance or censorship. The analysis combining data on the Tor anonymization network with protest event data demonstrates noticeable increases in Tor usage after days with many protest events but not days with single protest events.

dc.title:

Misinformation on social media has become a critical problem, particularly during a public health pandemic. Most social platforms today rely on users' voluntary reports to determine which news stories to fact-check first. Despite the importance, no prior work has explored the potential biases in such a reporting process. This work proposes a novel methodology to assess how users perceive truth or misinformation in online news stories. By conducting a large-scale survey (N = 15,000), we identify the possible biases in news perceptions and explore how partisan leanings influence the news selection algorithm for fact checking. Our survey reveals several perception biases or inaccuracies in estimating the truth level of stories. The first kind, called the total perception bias (TPB), is the aggregate difference in the ground truth and perceived truth level. The next two are the false-positive bias (FPB) and false-negative bias (FNB), which measures users' gullibility and cynicality of a given claim. We also propose ideological mean perception bias (IMPB), which quantifies a news story's ideological disputability. Collectively, these biases indicate that user perceptions are not correlated with the ground truth of new stories; users believe some stories to be more false and vice versa. This calls for the need to fact-check news stories that exhibit the most considerable perception biases first, which the current voluntary reporting does not offer. Based on these observations, we propose a new framework that can best leverage users' truth perceptions to remove false stories, correct misperceptions of users, or decrease ideological disagreements. We discuss how this new prioritizing scheme can aid platforms to significantly reduce the impact of fake news on user beliefs.

There are two main political economy explanations of the Eurocrisis. The labor market view regards cross-country differences in wage bargaining institutions as the root cause of the crisis. The finance view, instead, emphasizes cross-border financial flows and downplays labor market institutions. For the first time, we attempt to assess these two explanations jointly. We find that financial flows are better predictors of nominal wage growth than labor market institutions. At the same time, we show that wage moderation matters for bilateral export performance in the important case of Germany, but not for other countries. These results suggest that imposing wage moderation and labor market reforms onto the countries of the European periphery was unlikely to improve their plight. In contrast, stimulating wage growth in Germany might have contributed to rebalancing the Eurozone.

dc.title: