scholarly journals Large-Scale Computerized Text Analysis in Political Science: Opportunities and Challenges

2017 ◽  
Vol 20 (1) ◽  
pp. 529-544 ◽  
Author(s):  
John Wilkerson ◽  
Andreu Casas
Author(s):  
Natalie Shapira ◽  
Gal Lazarus ◽  
Yoav Goldberg ◽  
Eva Gilboa-Schechtman ◽  
Rivka Tuval-Mashiach ◽  
...  

Author(s):  
Kate G. Niederhoffer ◽  
James W. Pennebaker

Over two decades of research devoted to the writing paradigm has resulted in substantial findings that translating emotional events into words leads to profound social, psychological, and neural changes. How and why would constructing stories about important personal events be so beneficial? The chapter describes the writing paradigm used in this research, offering an overview of the research findings and examination of its historical antecedents. While the precise mechanisms through which a narrative heals are still unrealized, we review three underlying processes that might explain its power: emotional inhibition, cognitive processes, and linguistic processes that echo changes in social orientation. Most recently, advances in computerized text analysis, in addition to the rapid development of the Internet, have afforded a new lens on the psychological transformations achieved through the writing paradigm. Linguistic Inquiry and Word Count (LIWC) is one such computerized text analysis program that captures style and content words. Originally created to better understand the language of emotional upheaval and recovery, with a focus on content and emotional valence, more recent research has focused on subtle stylistic differences in function words such as pronouns, articles, and prepositions. These “junk words” have proven to be reliable markers of demographics, biological activity, depression, life stressors, deception, and status. The chapter briefly reviews recent LIWC-based research regarding the often-overlooked stylistic components of sharing one's story.


1983 ◽  
Vol 38 ◽  
pp. 1-9
Author(s):  
Herbert F. Weisberg

We are now entering a new era of computing in political science. The first era was marked by punched-card technology. Initially, the most sophisticated analyses possible were frequency counts and tables produced on a counter-sorter, a machine that specialized in chewing up data cards. By the early 1960s, batch processing on large mainframe computers became the predominant mode of data analysis, with turnaround time of up to a week. By the late 1960s, turnaround time was cut down to a matter of a few minutes and OSIRIS and then SPSS (and more recently SAS) were developed as general-purpose data analysis packages for the social sciences. Even today, use of these packages in batch mode remains one of the most efficient means of processing large-scale data analysis.


2021 ◽  
Vol 40 (3) ◽  
Author(s):  
Zhiyu Wang ◽  
Jingyu Wu ◽  
Guang Yu ◽  
Zhiping Song

In traditional historical research, interpreting historical documents subjectively and manually causes problems such as one-sided understanding, selective analysis, and one-way knowledge connection. In this study, we aim to use machine learning to automatically analyze and explore historical documents from a text analysis and visualization perspective. This technology solves the problem of large-scale historical data analysis that is difficult for humans to read and intuitively understand. In this study, we use the historical documents of the Qing Dynasty Hetu Dangse,preserved in the Archives of Liaoning Province, as data analysis samples. China’s Hetu Dangse is the largest Qing Dynasty thematic archive with Manchu and Chinese characters in the world. Through word frequency analysis, correlation analysis, co-word clustering, word2vec model, and SVM (Support Vector Machines) algorithms, we visualize historical documents, reveal the relationships between functions of the government departments in the Shengjing area of the Qing Dynasty, achieve the automatic classification of historical archives, improve the efficient use of historical materials as well as build connections between historical knowledge. Through this, archivists can be guided practically in historical materials’ management and compilation.


Author(s):  
Nonna Mayer ◽  
Vincent Tiberj

The boom in survey research, the increasing internationalization of political science, and the development of large-scale comparative projects have renewed the study of political culture and invalidated the notion of a French “exceptionalism.” But French scholars, influenced by Marxism, social history, and Bourdieu’s legacy of “critical sociology,” still have a different understanding of political culture, and prefer to use other concepts such as ideology. After a rapid overview of the founding studies and debates, this chapter shows how French research on political culture or cultures in the plural developed in its own way, and outlines the major challenges it is facing today on issues such as race and ethnicity, gender, globalization, and poverty.


Author(s):  
Wouter van Atteveldt ◽  
Kasper Welbers ◽  
Mariken van der Velden

Analyzing political text can answer many pressing questions in political science, from understanding political ideology to mapping the effects of censorship in authoritarian states. This makes the study of political text and speech an important part of the political science methodological toolbox. The confluence of increasing availability of large digital text collections, plentiful computational power, and methodological innovations has led to many researchers adopting techniques of automatic text analysis for coding and analyzing textual data. In what is sometimes termed the “text as data” approach, texts are converted to a numerical representation, and various techniques such as dictionary analysis, automatic scaling, topic modeling, and machine learning are used to find patterns in and test hypotheses on these data. These methods all make certain assumptions and need to be validated to assess their fitness for any particular task and domain.


2015 ◽  
Vol 48 (03) ◽  
pp. 478-482 ◽  
Author(s):  
Daniel J. Mallinson ◽  
Zachary D. Baumann

ABSTRACTLecture-capture software allows instructors to record their class presentations for students to review as necessary. Although this technology has long been considered too expensive for large-scale use, it is quickly becoming ubiquitous and deployable using ordinary computers and consumer-grade software. Using survey and final-grade data from a three-semester trial in a large introductory-level political science course, the authors demonstrate students almost universally approve of the technology and support its use in future classes. Students are most likely to use recordings when they study for exams and catch up on material after being absent from class. Additionally, certain subgroups—primarily international students and those who are performing poorly in the class—are more likely to watch archived recordings. However, these data demonstrate that positive evaluations and increased usage may not translate into better grades; viewing lectures does not appear to substantially improve individual performance.


1985 ◽  
Vol 47 (3) ◽  
pp. 390-410
Author(s):  
Raghuveer Singh

Political science is in a state of crisis today. The crisis is the result of the scientistic predicament. Man has become the victim of his own reason and knowledge. Scientific rationality and value-neutral theories of knowledge lead to the eclipse of the public realm and the growth of social regimentation, mass manipulation, large-scale indoctrination and totalitarian domination. As a result, the homo politicus is reduced to the homo faber and the animal laboran. What is required is a radical shift in our intellectual perspective. Phenomenological and linguistic-analytical theories of action are inadequate to provide a sound basis for political science. Philosphia perennis alone can restore to politics its full glory and splendor.


1971 ◽  
Vol 65 (1) ◽  
pp. 11-27 ◽  
Author(s):  
Karl W. Deutsch

This paper is a revision of the Presidential Address delivered to the 66th Annual Meeting of the American Political Science Association, Los Angeles, California, September 10, 1970. It identifies nine aspects of political theories: storage and retrieval of memories; assistance to insight; simplification of knowledge; heuristic effectiveness; self-critical cognition; normative awareness of values; scientifically testable knowledge; pragmatic skills; and wisdom, or second-order knowledge of what contexts are worth choosing—a wisdom subject to the possibility of radical restructuring. These nine aspects of theory form an integrated production cycle of knowledge. “Scientific” and “humanistic” political theorists need each other to understand the central task of politics: the collective self-determination of societies. To appraise this steering performance of political systems, large amounts of empirical data as indicators of social performance are indispensable. Political science has grown in knowledge of cases, data, research methods, and sensitivity to problems of disadvantaged groups and of the individual. It is learning to recognize qualities and patterns, verify the limited truth content of theories, and be more critical of its societies and of itself. It needs to increase research on implementation of insights, on positive proposals for reform, changes in political wisdom, and on the abolition of poverty and large-scale war. For these tasks, cognitive contributions from political theory are indispensable; working to make them remains a moral commitment.


Sign in / Sign up

Export Citation Format

Share Document