An important part of our information-gathering behavior has always been to find out what other people think. With the growing availability and popularity of opinion-rich resources such as online review sites and personal blogs, new opportunities and challenges arise as people now can, and do, actively use information technologies to seek out and understand the opinions of others. The sudden eruption of activity in the area of opinion mining and sentiment analysis, which deals with the computational treatment of opinion, sentiment, and subjectivity in text, has thus occurred at least in part as a direct response to the surge of interest in new systems that deal directly with opinions as a first-class object.

This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems. Our focus is on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis. We include material on summarization of evaluative text and on broader issues regarding privacy, manipulation, and economic impact that the development of opinion-oriented information-access services gives rise to. To facilitate future work, a discussion of available resources, benchmark datasets, and evaluation campaigns is also provided.

/pdf/opinion-mining-and-sentiment-analysis-3v5ya3qqiw.pdf

Opinion Mining and Sentiment Analysis

Emotion and Adaptation

Politics and political conflict often occur in the written and spoken word. Scholars have long recognized this, but the massive costs of analyzing even moderately sized collections of texts have hindered their use in political science research. Here lies the promise of automated text analysis: it substantially reduces the costs of analyzing large collections of text. We provide a guide to this exciting new area of research and show how, in many instances, the methods have already obtained part of their promise. But there are pitfalls to using automated methods—they are no substitute for careful thought and close reading and require extensive and problem-specific validation. We survey a wide range of new methods, provide guidance on how to validate the output of the models, and clarify misconceptions and errors in the literature. To conclude, we argue that for automated text methods to become a standard tool for political scientists, methodologists must contribute new methods and new methods of validation. Language is the medium for politics and political conflict. Candidates debate and state policy positions during a campaign. Once elected, representatives write and debate legislation. After laws are passed, bureaucrats solicit comments before they issue regulations. Nations regularly negotiate and then sign peace treaties, with language that signals the motivations and relative power of the countries involved. News reports document the day-to-day affairs of international relations that provide a detailed picture of conflict and cooperation. Individual candidates and political parties articulate their views through party platforms and manifestos. Terrorist groups even reveal their preferences and goals through recruiting materials, magazines, and public statements. These examples, and many others throughout political science, show that to understand what politics is about we need to know what political actors are saying and writing. Recognizing that language is central to the study of politics is not new. To the contrary, scholars of politics have long recognized that much of politics is expressed in words. But scholars have struggled when using texts to make inferences about politics. The primary problem is volume: there are simply too many political texts. Rarely are scholars able to manually read all the texts in even moderately sized corpora. And hiring coders to manually read all documents is still very expensive. The result is that

/pdf/text-as-data-the-promise-and-pitfalls-of-automatic-content-33q0hxlgsq.pdf

Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts

The Political Consciousness of Post-Industrialism@@@The Silent Revolution: Changing Values and Political Styles among Western Publics.

Ethnic Groups in Conflict

We present a new way of extracting policy positions from political texts that treats texts not as discourses to be understood and interpreted but rather, as data in the form of words. We compare this approach to previous methods of text analysis and use it to replicate published estimates of the policy positions of political parties in Britain and Ireland, on both economic and social policy dimensions. We “export” the method to a non-English-language environment, analyzing the policy positions of German parties, including the PDS as it entered the former West German party system. Finally, we extend its application beyond the analysis of party manifestos, to the estimation of political positions from legislative speeches. Our “language-blind” word scoring technique successfully replicates published policy estimates without the substantial costs of time and labor that these require. Furthermore, unlike in any previous method for extracting policy positions from political texts, we provide uncertainty measures for our estimates, allowing analysts to make informed judgments of the extent to which differences between two estimated policy positions can be viewed as significant or merely as products of measurement error.We thank Raj Chari, Gary King, Michael McDonald, Gail McElroy, and three anonymous reviewers for comments on drafts of this paper.

https://www.kenbenoit.net/pdfs/WORDSCORESAPSR.pdf

Extracting policy positions from political texts using words as data

The analysis of policy-based party competition will not make serious progress beyond the constraints of (a) the unitary actor assumption and (b) a static approach to analyzing party competition between elections until a method is available for deriving reliable and valid time-series estimates of the policy positions of large numbers of political actors. Retrospective estimation of these positions in past party systems will require a method for estimating policy positions from political texts. Previous hand-coding content analysis schemes deal with policy emphasis rather than policy positions. We propose a new hand-coding scheme for policy positions, together with a new English language computer-coding scheme that is compatible with this. We apply both schemes to party manifestos from Britain and Ireland in 1992 and 1997 and cross validate the resulting estimates with those derived from quite independent expert surveys and with previous manifesto analyses. There is a high degree of cross validation between coding methods, including computer coding. This implies that it is indeed possible to use computer-coded content analysis to derive reliable and valid estimates of policy positions from political texts. This will allow vast volumes of text to be coded, including texts generated by individuals and other internal party actors, allowing the empirical elaboration of dynamic rather than static models of party competition that move beyond the unitary actor assumption. eriving reliable and valid estimates of the policy positions of key actors is fundamental to the analysis of political competition. Various systematic methods have been used to do this, including surveys of voters, politicians, and political scientists, and the content analysis of policy documents. Each method has advantages and disadvantages but, for both theoretical and pragmatic reasons, policy documents represent a core source of information about the policy positions of political actors. We explore various ways to extract information about policy positions from political texts. We are particularly interested in using computer-coding techniques to derive reliable and valid estimates of the policy positions of political actors. This is not mere laziness on our part, a lack of stomach for the hard graft of expert coding. If analyses of party competition are to move beyond both static models and a view of political parties as unitary actors, this requires information on the policy positions of actors inside political parties and on the development of these over time and between elections. The laborious expert "hand-coding" of text is simply not a viable method for estimating the policy positions of huge numbers of political actors, for example, all members of a legislature. Any serious attempt to operationalize a model of internal party policy competition, or of dynamic policy-based party competition or coalition government between elections, implies using computer-coding for estimating the policy positions of key political actors. We first review existing methods for estimating policy positions from political texts. These have for the most part concentrated on the expert coding of party manifestos. We then suggest ways to improve these, dealing with both expertand computer-coded content analysis. We then explore the impact of our suggestions upon estimates of party policy positions derived from British and Irish manifestos issued during the 1992 and 1997 general elections in each country, positions for which a range of

Estimating policy positions from political texts

Are referendums on EU treaties decided by voters’ attitudes to Europe (the ‘issue-voting’ explanation) or by voters’ attitudes to their national political parties and incumbent national government ...

/pdf/second-order-versus-issue-voting-effects-in-eu-referendums-3kft16q648.pdf

‘Second-order’ versus ‘Issue-voting’ Effects in EU Referendums: Evidence from the Irish Nice Treaty Referendums

Factors relating to identity and to economics have been shown to be important predictors of attitudes towards the European Union (EU). In this article, we show that the impact of identity is conditional on economic context. First, living in a member state that receives relatively high levels of EU funding acts as a ‘buffer’, diluting the impact of an exclusive national identity on Euroscepticism. Second, living in a relatively wealthy member state, with its associated attractiveness for economic migrants, increases the salience of economic xenophobia as a driver of sceptical attitudes. These results highlight the importance of seeing theories of attitude formation (such as economic and identity theories) not as competitors but rather as complementary, with the predictive strength of one theoretical approach (identity) being a function of system-level variation in factors relating to the other theoretical approach (macro-level economic conditions).

The Macroeconomic Factors Conditioning the Impact of Identity on Attitudes towards the EU

List of tables List of figures 1. Introduction 2. How people voted 3. The evidence for cleavage politics 4. The extent and meaning of party attachment 5. Credit and blame for the 'Celtic Tiger' 6. Leaders and their parties 7. Grassroots campaigning 8. Parties or candidates? 9. Adding it all up 10. Voter turnout: the need for facilitation and mobilisation 11. Conclusion References Appendix I: Details of the survey Appendix II: The Electoral System Appendix III: Table for Chapter 9 Appendix III: Questionnaire with frequency distributions Index -- .

John Garry

Papers

Extracting policy positions from political texts using words as data

Estimating policy positions from political texts

‘Second-order’ versus ‘Issue-voting’ Effects in EU Referendums: Evidence from the Irish Nice Treaty Referendums

The Macroeconomic Factors Conditioning the Impact of Identity on Attitudes towards the EU

The Irish voter: The nature of electoral competition in the Republic of Ireland