Automated text analysis in psychology: methods, applications, and future developments

被引:86
作者
Iliev, Rumen [1 ]
Dehghani, Morteza [2 ]
Sagi, Eyal [3 ]
机构
[1] Univ Michigan, Ann Arbor, MI 48109 USA
[2] Univ So Calif, Los Angeles, CA 90089 USA
[3] Northwestern Univ, Evanston, IL 60208 USA
关键词
automated text analysis; psychological variables; demographics; technology; big data; psycho-informatics; LATENT SEMANTIC ANALYSIS; LANGUAGE USE; SEPTEMBER; 11; DOCUMENTS; CULTURE; GERMAN; WORDS; BLOGS;
D O I
10.1017/langcog.2014.30
中图分类号
H0 [语言学];
学科分类号
030303 ; 0501 ; 050102 ;
摘要
Recent years have seen rapid developments in automated text analysis methods focused on measuring psychological and demographic properties. While this development has mainly been driven by computer scientists and computational linguists, such methods can be of great value for social scientists in general, and for psychologists in particular. In this paper, we review some of the most popular approaches to automated text analysis from the perspective of social scientists, and give examples of their applications in different theoretical domains. After describing some of the pros and cons of these methods, we speculate about future methodological developments, and how they might change social sciences. We conclude that, despite the fact that current methods have many disadvantages and pitfalls compared to more traditional methods of data collection, the constant increase of computational power and the wide availability of textual data will inevitably make automated text analysis a common tool for psychologists.
引用
收藏
页码:265 / 290
页数:26
相关论文
共 101 条
[21]   Linguistic markers of psychological change surrounding September 11, 2001 [J].
Cohn, MA ;
Mehl, MR ;
Pennebaker, JW .
PSYCHOLOGICAL SCIENCE, 2004, 15 (10) :687-693
[22]  
D'Mello S., 2009, P 2009 C ART INT ED
[23]   Language and Discourse Are Powerful Signals of Student Emotions during Tutoring [J].
D'Mello, Sidney K. ;
Graesser, Art .
IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES, 2012, 5 (04) :304-317
[24]   Computer assessment of interview data using latent semantic analysis [J].
Dam, Gregory ;
Kaufmann, Stefan .
BEHAVIOR RESEARCH METHODS, 2008, 40 (01) :8-20
[25]  
Dave K., 2003, PAPER PRESENTED P 12, P519, DOI [DOI 10.1145/775152.775226, 10.1145/775152.775226]
[26]   Analyzing Political Rhetoric in Conservative and Liberal Weblogs Related to the Construction of the "Ground Zero Mosque" [J].
Dehghani, Morteza ;
Sagae, Kenji ;
Sachdeva, Sonya ;
Gratch, Jonathan .
JOURNAL OF INFORMATION TECHNOLOGY & POLITICS, 2014, 11 (01) :1-14
[27]   Epistemologies in the Text of Children's Books: Native- and non-Native-authored books [J].
Dehghani, Morteza ;
Bang, Megan ;
Medin, Douglas ;
Marin, Ananda ;
Leddon, Erin ;
Waxman, Sandra .
INTERNATIONAL JOURNAL OF SCIENCE EDUCATION, 2013, 35 (13) :2133-2151
[28]   Authorship attribution with support vector machines [J].
Diederich, J ;
Kindermann, O ;
Leopold, E ;
Paass, G .
APPLIED INTELLIGENCE, 2003, 19 (1-2) :109-123
[29]   Language and Ideology in Congress [J].
Diermeier, Daniel ;
Godbout, Jean-Francois ;
Yu, Bei ;
Kaufmann, Stefan .
BRITISH JOURNAL OF POLITICAL SCIENCE, 2012, 42 :31-55
[30]   TOWARD AN EPISTEMOLOGY OF PHYSICS [J].
DISESSA, AA .
COGNITION AND INSTRUCTION, 1993, 10 (2-3) :105-225