Martin Haselmayer

Sentiment analysis of political communication: combining a dictionary approach with crowdcoding

Abstract Sentiment is important in studies of news values, public opinion, negative campaigning or political polarization and an explosive expansion of digital textual data and fast progress in automated text analysis provide vast opportunities for innovative social science research. Unfortunately, tools currently available for automated sentiment analysis are mostly restricted to English texts and require considerable contextual adaption to produce valid results. We present a procedure for collecting fine-grained sentiment scores through crowdcoding to build a negative sentiment dictionary in a language and for a domain of choice. The dictionary enables the analysis of large text corpora that resource-intensive hand-coding struggles to cope with. We calculate the tonality of sentences from dictionary words and we validate these estimates with results from manual coding. The results show that the crowdbased dictionary provides efficient and valid measurement of sentiment. Empirical examples illustrate its use by analyzing the tonality of party statements and media reports.

Partisan Bias in Message Selection: Media Gatekeeping of Party Press Releases

Parties try to shape media coverage in ways that are favorable to them, but what determines whether media outlets pick up and report on party messages? Based on content analyses of 1,496 party press releases and 6,512 media reports from the 2013 Austrian parliamentary election campaign, we show that media coverage of individual party messages is influenced not just by news factors, but also by partisan bias. The media are therefore more likely to report on messages from parties their readers favor. Importantly, this effect is greater rather than weaker when these messages have high news value. These findings have important implications for understanding the media’s role in elections and representative democracies in general.

More than Bags of Words: Sentiment Analysis with Word Embeddings

ABSTRACT Moving beyond the dominant bag-of-words approach to sentiment analysis we introduce an alternative procedure based on distributed word embeddings. The strength of word embeddings is the ability to capture similarities in word meaning. We use word embeddings as part of a supervised machine learning procedure which estimates levels of negativity in parliamentary speeches. The procedure’s accuracy is evaluated with crowdcoded training sentences; its external validity through a study of patterns of negativity in Austrian parliamentary speeches. The results show the potential of the word embeddings approach for sentiment analysis in the social sciences.

Fighting for attention: Media coverage of negative campaign messages

The article studies whether and how negative campaigning is a successful strategy for attaining media attention. It combines extensive content analyses of party and news texts with public opinion surveys to study the success of individual press releases in making the news. The empirical analysis draws on 1496 party press releases and 6512 news reports in all national media outlets during the final 6 weeks of Austria’s 2013 general election campaign. We find that negative campaigning is a successful strategy to attract the attention of journalists and editors. It is particularly relevant for rank-and-file politicians, who lack the intrinsic news value of high public or party office, and for messages that focus on a rival’s best issues. These findings have broader implications for understanding party strategies and ‘negativity bias’ in the news.

Who Gets into the Papers? Party Campaign Messages and the Media

Parties and politicians want their messages to generate media coverage and thereby reach voters. This article examines how attributes related to content and sender affect whether party messages are likely to get media attention. Based on content analyses of 1,613 party press releases and 6,512 media reports in a parliamentary, multiparty context, we suggest that party messages are more likely to make it into the news if they address concerns that are already important to the media or other parties. Discussing these issues may particularly help opposition parties and lower-profile politicians get media attention. These results confirm the importance of agenda setting and gatekeeping, shed light on the potential success of party strategies, and have implications for political fairness and representation.

Friendly fire? Negative campaigning among coalition partners

In democracies with multi-party competition, government parties face a dual challenge in election campaigns: on the one hand, they have to compete against and criticize their coalition partners. On the other hand, they should avoid virulent attacks on their partners to preserve their chances of future collaboration in government. Going beyond a dichotomous operationalization of negative campaigning, this manuscript analyses the tonality and volume of negative campaigning. Studying 3030 party press releases in four national Austrian election campaigns, different patterns for the tonality and frequency of negative campaigning reflect the electoral dilemma of government parties. Coalition parties criticize each other abundantly but refrain from ‘burning bridges’ with their partners through virulent attacks. These findings have implications for studying negative campaigning and coalition politics.