Automatic prediction of gender, political affiliation, and age in Swedish politicians from the wording of their speeches--A comparative study of classifiability

Dahllöf, Mats

doi:10.1093/llc/fqs010

Cited by 24 publications

(29 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A total of eleven author characteristics were included in the meta-data. Some of these are social characteristics, traditional to sociolinguistic studies of language variation, and some of these are conceptual characteristics related to political ideology that are somewhat new to studies of language variation (Laver et al, 2003;Thomas et al, 2006;Diermeier et al, 2011;Dahllof, 2012;Iyyer et al, 2014). The idea behind the conceptual characteristics is that the speakers in this data set form speech communities based on shared ideologies and that these speech communities engage in an internal dialogue and partake of the same media sources.…”

Section: Data Setmentioning

confidence: 99%

“…This clustering is not a new task, on the one hand, because much work has already been done on profiling authors according to various biographical (Koppel et al, 2003;Argamon et al, 2009a,b;Mukherjee and Liu, 2010;Nguyen et al, 2011;Sarawgi et al, 2011) and political (Laver et al, 2003;Yu et al, 2008;Diermeier et al, 2011;Dahllof, 2012;Iyyer et al, 2014) attributes. On the other hand, the ability to cluster texts using predicted author profiles is a new approach not possible in previous work which (1) did not use as many profiles and (2) did not combine biographical and political profiles together.…”

Section: Profile-based Author Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

Profile-based authorship analysis

Dunn

Argamon

Rasooli

et al. 2015

Digital Scholarship Humanities

View full text Add to dashboard Cite

This article presents a profile-based authorship analysis method which first categorizes texts according to social and conceptual characteristics of their author (e.g. Sex and Political Ideology) and then combines these profiles for two authorship analysis tasks: (1) determining shared authorship of pairs of texts without a set of candidate authors and (2) clustering texts according to characteristics of their authors in order to provide an analysis of the types of individuals represented in the data set. The first task outperforms Burrows' Delta by a wide margin on short texts and a small margin on long texts. The second task has no such benchmark with existing methods. The data set for evaluating the method consists of speeches from the US House and Senate from 1995 to 2013. This data set contains both a large number of texts (42,000 in the test sets) and a large number of speakers (over 800). The article shows that this approach to authorship analysis is more accurate than existing approaches given a data set with hundreds of authors. Further, this profile-based method makes new types of analysis possible by looking at types of individuals as well as at specific individuals.

show abstract

Section: Data Setmentioning

confidence: 99%

Section: Profile-based Author Clusteringmentioning

confidence: 99%

Profile-based authorship analysis

Dunn

Argamon

Rasooli

et al. 2015

Digital Scholarship Humanities

View full text Add to dashboard Cite

show abstract

“…Similar to our political affiliation task, a line of research was devoted to discover the political affiliations of informal web-based contents like news ar-ticles [29], weblogs [4], political speeches [30] and web documents [3]. Political datasets such as debates and tweets are explored for classifying user stances [31].…”

Section: Related Workmentioning

confidence: 99%

An Integrated Model for User Attribute Discovery: A Case Study on Political Affiliation Identification

Gottipati

Qiu

Liu

et al. 2014

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Discovering user demographic attributes from social media is a problem of considerable interest. The problem setting can be generalized to include three components-users, topics and behaviors. In recent studies on this problem, however, the behavior between users and topics are not effectively incorporated. In our work, we proposed an integrated unsupervised model which takes into consideration all the three components integral to the task. Furthermore, our model incorporates collaborative filtering with probabilistic matrix factorization to solve the data sparsity problem, a computational challenge common to all such tasks. We evaluated our method on a case study of user political affiliation identification, and compared against state-of-the-art baselines. Our model achieved an accuracy of 70.1% for user party detection task.

show abstract

“…We study language wrt style, i.e., male and female style of the language usage by applying computational stylistics or stylometry. Stylometry is based on the two hypotheses: (1) human stylome hypothesis, i.e., each individual has a unique style (Van Halteren et al, 2005); (2) unique style of individual can be measured (Stamatatos, 2009), stylometry allows gaining meta-knowledge (Daelemans, 2013), i.e., what can be learned from the text about the author -gender (Luyckx et al, 2006;Argamon et al, 2003;Cheng et al, 2011;, age (Dahllöf, 2012), psychological characteristics (Luyckx and Daelemans, 2008), political affiliation (Dahllöf, 2012), etc.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing

2017

View full text Add to dashboard Cite

The Workshops have been convening for over a decade, with a clear vision and purpose. On one hand, the languages from the Balto-Slavic group play an important role due to their widespread use and diverse cultural heritage. These languages are spoken by about one third of all speakers of the official languages of the European Union, and by over 400 million speakers worldwide. The political and economic developments in Central and Eastern Europe place societies where Balto-Slavic languages are spoken at the center of rapid technological advancement and the growing European consumer markets.On the other hand, research on theoretical and applied NLP in some of these languages still lags behind the "major" languages, such as English and other West European languages. In comparison to English, which has dominated the digital world since the advent of the Internet, many of these languages still lack resources, processing tools and applications-especially those with smaller speaker bases.The Balto-Slavic languages pose a wealth of fascinating scientific challenges. The linguistic phenomena specific to the Balto-Slavic languages-complex morphology and free word order-present non-trivial problems for construction of NLP tools, and require rich morphological and syntactic resources. This view is also reflected in Serge Sharoff's invited talk on "Pan-Slavic NLP." In the talk, he discusses an ambitious project on language adaptation-ways to adapt tools and resources among closely related languages, such as those in the Slavic group.The BSNLP Workshops aim to bring together academic researchers and industry specialists in NLP for Balto-Slavic languages. We aim to stimulate research and to foster the creation and dissemination of tools and resources. The Workshop serves as a forum for exchange of ideas and experience and for discussing shared problems. One fascinating aspect of this group of languages is their structural similarity, as well as an easily recognizable lexical and inflectional inventory spanning the entire group, which-despite the lack of mutual intelligibility-creates a special environment in which researchers can fully appreciate the shared problems and solutions.As a result of discussions at the previous BSNLP Workshops, to help catalyze collaboration, this year we have organized the first SIGSLAV Challenge: a shared task on multilingual named entity recognition. We have built a dataset, which allows systems to be evaluated on recognizing mentions of named entities in Web documents, their normalization/lemmatization, and cross-lingual matching. The Challenge initially covers seven Slavic languages, and it is intended as a first version of an evaluation standard to be expanded in the future.We received 24 regular submissions, 14 of which were accepted for presentation.The papers cover a wide range of topics. Two papers relate to lexical semantics, four to development of linguistic resources, and four to information filtering, information retrieval, and information extraction. Four papers cover topics related to...

show abstract

Automatic prediction of gender, political affiliation, and age in Swedish politicians from the wording of their speeches--A comparative study of classifiability

Cited by 24 publications

References 4 publications

Profile-based authorship analysis

Profile-based authorship analysis

An Integrated Model for User Attribute Discovery: A Case Study on Political Affiliation Identification

Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing

Contact Info

Product

Resources

About