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

Haselmayer, Martin; Jenny, Marcelo

doi:10.1007/s11135-016-0412-4

Cited by 158 publications

(108 citation statements)

References 63 publications

(97 reference statements)

Supporting

Mentioning

104

Contrasting

Unclassified

Order By: Relevance

“…A growing body of literature has begun to investigate the type of language employed in campaign materials such as, for instance, the tone or sentiment in campaign messages (Haselmayer & Jenny 2016;Young & Soroka 2012). A growing body of literature has begun to investigate the type of language employed in campaign materials such as, for instance, the tone or sentiment in campaign messages (Haselmayer & Jenny 2016;Young & Soroka 2012).…”

Section: Who Produces Simple Messages and How It Matters For Votersmentioning

confidence: 99%

Simple politics for the people? Complexity in campaign messages and political knowledge

Bischof

Senninger

2017

European J Political Res

View full text Add to dashboard Cite

Which parties use simple language in their campaign messages, and do simple campaign messages resonate with voters’ information about parties? This study introduces a novel link between the language applied during election campaigns and citizens’ ability to position parties in the ideological space. To this end, how complexity of campaign messages varies across parties as well as how it affects voters’ knowledge about party positions is investigated. Theoretically, it is suggested that populist parties are more likely to simplify their campaign messages to demarcate themselves from mainstream competitors. In turn, voters should perceive and process simpler campaign messages better and, therefore, have more knowledge about the position of parties that communicate simpler campaign messages. The article presents and validates a measure of complexity and uses it to assess the language of manifestos in Austria and Germany in the period 1945–2013. It shows that political parties, in general, use barely comprehensible language to communicate their policy positions. However, differences between parties exist and support is found for the conjecture about populist parties as they employ significantly less complex language in their manifestos. Second, evidence is found that individuals are better able to place parties in the ideological space if parties use less complex campaign messages. The findings lead to greater understanding of mass‐elite linkages during election campaigns and have important consequences for the future analysis of manifesto data.

show abstract

Section: Who Produces Simple Messages and How It Matters For Votersmentioning

confidence: 99%

Simple politics for the people? Complexity in campaign messages and political knowledge

Bischof

Senninger

2017

European J Political Res

View full text Add to dashboard Cite

show abstract

“…This is due to the lack of relevant studies – political science exceptions are Benoit et al. (), Haselmayer and Jenny () and Berinsky et al. () – and the studies that do exist often draw on advances in computational linguistics.…”

Section: Procedure: Implementing the Six Different Scenarios On Crowdmentioning

confidence: 99%

“…This simple but powerful idea that good collective decisions can emanate from various averaged independent judgements of non-experts is long discussed in academia, business and popular science (see Surowiecki 2004;Lehman & Zobel 2017). Yet, notwithstanding instructive earlier studies with positive conclusions regarding the validity of crowd-coded data (e.g., Berinsky et al 2014;Haselmayer & Jenny 2016;Lind et al 2017), it seems fair to say that crowd-coding is only starting to gain traction in political science at large since Benoit et al (2016) have convincingly argued that the results of expert judgements -still considered the gold standard by many (e.g., when it comes to the location of parties) -can be matched with crowd-coding, at least for simple coding tasks. This is significant, since experts are expensive and in short supply and automated (coding) methods are not yet good enough at extracting meaning (Benoit et al 2016: 280).…”

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

Can the online crowd match real expert judgments? How task complexity and coder location affect the validity of crowd‐coded data

Horn

2018

European J Political Res

View full text Add to dashboard Cite

Crowd‐coding is a novel technique that allows for fast, affordable and reproducible online categorisation of large numbers of statements. It combines judgements by multiple, paid, non‐expert coders to avoid miscoding(s). It has been argued that crowd‐coding could replace expert judgements, using the coding of political texts as an example in which both strategies produce similar results. Since crowd‐coding yields the potential to extend the replication standard to data production and to ‘scale’ coding schemes based on a modest number of carefully devised test questions and answers, it is important that its possibilities and limitations are better understood. While previous results for low complexity coding tasks are encouraging, this study assesses whether and under what conditions simple and complex coding tasks can be outsourced to the crowd without sacrificing content validity in return for scalability. The simple task is to decide whether a party statement counts as positive reference to a concept – in this case: equality. The complex task is to distinguish between five concepts of equality. To account for the crowd‐coder's contextual knowledge, the IP restrictions are varied. The basis for comparisons is 1,404 party statements, coded by experts and the crowd (resulting in 30,000 online judgements). Comparisons of the expert‐crowd match at the level of statements and party manifestos show that the results are substantively similar even for the complex task, suggesting that complex category schemes can be scaled via crowd‐coding. The match is only slightly higher when IP restrictions are used as an approximation of coder expertise.

show abstract

“…SENTIWS has been used in studies of political communication (Haselmayer & Jenny, 2016), or art and literature (Zehe et al, 2016). The second general language dictionary was created by Wolf et al (2008), who adapted the English version of the Linguistic Inquiry Word Count to the German language.…”

Section: German Language Dictionariesmentioning

confidence: 99%

CEO-Speeches and Stock Returns

Bannier

Pauls

2017

SSRN Journal

View full text Add to dashboard Cite

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

Cited by 158 publications

References 63 publications

Simple politics for the people? Complexity in campaign messages and political knowledge

Simple politics for the people? Complexity in campaign messages and political knowledge

Can the online crowd match real expert judgments? How task complexity and coder location affect the validity of crowd‐coded data

CEO-Speeches and Stock Returns

Contact Info

Product

Resources

About