Rakovics Zsófia (2022): Demonstrating potentials in the application of the Temporal Positive Pointwise Mutual Information (TPPMI) temporal word-embedding model – The change in meaning of the words in the prime ministers’ speeches

2022.07.03. Publication The layers of political public sphere in Hungary (2001–2020)

Zsófia Rakovics’s new publication is out now which is published in the new compilation ’Van új a nap alatt’ from Angelusz Róbert College for Advanced Studies. In relation to our OTKA research, the paper can be accessible in Hungarian.

ELTE-TINLAB workshop

2022.06.27. Presentation Discursive framing of depression in online health communities

On 22nd June our ELTE-TINLAB research team hosted a workshop titled ‘Online lay depression discourses – research summary and recommendations by the ELTE-TINLAB depression forum research team’, inviting professionals involved in health care and e-mental health.

Our research last semester was based on two questions: How are the online depression forum discourses affected by the covid? And, from a sociological perspective, how do these forums serve as agents of socialization?

The members of the ELTE-TINLAB depression forum research team:

Principal investigator: Domonkos Sik

Senior researcher: Renáta Németh

Researchers: Jakab Buda, Márton Rakovics, Bendegúz Zaboretzky, Eszter Katona

Clinical consultant: Máté Kapitány-Föveny

Our project is supported by the Social Innovation National Laboratory (TINLAB), NKFIH-875-4/2020

Zsófia Rakovics, Márton Rakovics (2022): Semantic evolution of words in Hungarian PM Viktor Orbán’s speeches using a temporal word embedding model focusing on the issue of migration

2022.06.22. Conference poster The layers of political public sphere in Hungary (2001–2020)

Zsófia Rakovics and Márton Rakovics will display the results of their research entitledSemantic evolution of words in Hungarian PM Viktor Orbán’s speeches using a temporal word embedding model focusing on the issue of migration” at the poster section of the 8th International Conference on Computational Social Science IC2S2 (The University of Chicago Booth School of Business, Chicago, IL, USA), July 19-22, 2022.

Zsófia Rakovics (2022): Analyzing the semantic evolution of words related to migration in prime ministerial speeches using a temporal word embedding model

2022.06.03. Presentation The layers of political public sphere in Hungary (2001–2020)

Zsófia Rakovics gave a presentation at the annual conference of the Centre for Social Sciences, entitled “Analyzing the semantic evolution of words related to migration in prime ministerial speeches using a temporal word embedding model” on 3 June, 2022.

Emese Tímea Tóth (2022): Analysis of the Twitter discourse on sustainability using the methods of natural language processing

2022.06.03. Presentation The layers of political public sphere in Hungary (2001–2020)

Tímea Emese Tóth gave a presentation entitled “Analysis of the Twitter discourse on sustainability using the method of natural language processing” at the Centre for Social Sciences’ annual conference on June 3, 2022. The performance was a great success, with Emese receiving the Special Award for the Best Doctoral Presentation in the non-doctoral section.

RC2S2 researchers at the TK conference

2022.06.01. Presentation

06.03.2022, Friday

Simultaneous sections. Sociology’s place in historical researches. | WHERE? >> room K.012 | WHEN? >> 06.03., Friday 9AM starting | RC2S2 participant >> Ildikó Barna, Alexandra M. Szabó

Simultaneous sections.  Application of text analytics in social sciences. | WHERE? >> rooms K.013 and K.014 | WHEN? >> 06.03., Friday 11 AM starting | RC2S2 participant >> Eszter Katona, Árpád Knap, Zsófia Rakovics, Tímea Emese Tóth

The conference can be attended in person and online.

Tímea Emese Tóth (2021): Analysis of the Twitter Discourse on Sustainability Using Natural Language Processing

2022.05.24. Publication The layers of political public sphere in Hungary (2001–2020)

Emese Tímea Tóth, a member of our research group, writes about the sustainability discourse on Twitter. Mesi’s doctoral topic, related to our OTKA research, examines the discourse of sustainability in the triad of political publicity, online media platforms and the lay public.

Poster of the members of our research group at the CEU Data Stories exhibition

2022.05.23. Poszter

A visualisation of Fanni, Eszter and Árpád’s previous research was also exhibited at this year’s Data Stories event. https://datastoriesceu.org/gallery/happy-birthday-information-society

The primary aim of the research is to use NLP tools to review the themes that the journal has introduced into the domestic discourse of “information society studies” over the past 15 years, and to explore the thematic structure of the journal. In addition to content analysis, the research provides insights into the co-authorship network of the journal’s contributors and the relationship between authors and specific topics.

To read: https://doi.org/10.22503/inftars.XXI.2021.1.1

To view: https://inftars.infonia.hu/inftars20?lang=hu

Ildikó Barna, Árpád Knap (2022): Analysis of the Thematic Structure and Discursive Framing in Articles about Trianon and the Holocaust in the Online Hungarian Press Using LDA Topic Modelling

2022.05.16. Publication The layers of political public sphere in Hungary (2001–2020)

The latest publication by Ildikó Barna and Árpád Knap was published in the journal Nationalities Papers (D1). In their paper, they examined the thematic structure and discursive framing in newspaper articles related to the Trianon Peace Treaty and the Holocaust using LDA topic models and qualitative analysis. The article is open access.

Eszter Katona (2022): Using algorithms to track corruption. Applications of natural language processing in corruption research

2022.04.22. Presentation Corruption in Online Editorial Media

Eszter Katona, a member of our research group, gave a presentation at the ‘There’s something new under the sun’ conference on innovative methods. Eszter’s presentation was titled ‘Using algorithms to track corruption. Applications of natural language processing in corruption research’, and was related to her doctoral research.

Zsófia Rakovics (2022): Demonstrating the potential of Temporal Positive Pointwise Mutual Information (TPPMI) temporal word embedding model – Semantic evolution of words in prime ministerial speeches

2022.04.22. Presentation The layers of political public sphere in Hungary (2001–2020)

Zsófia Rakovics gave a presentation entitled Demonstrating the potential of Temporal Positive Pointwise Mutual Information (TPPMI) temporal word embedding model – Semantic evolution of words in prime ministerial speeches at the ’Van új a nap alatt’ conference of the ELTE Angelusz Róbert College for Advanced Studies in Social Sciences, 2022.04.22. The work will also be published in the accompanying conference proceedings (in print).

Eszter Katona, Mihály Fazekas (2022): Hidden barriers to open competition: Using text mining to uncover corrupt restrictions to competition in Public Procurement

2022.04.20. Előadás

Eszter Katona, a member of our research team, also presented a paper co-authored by her co-chair at the ECPR workshop on measuring corruption. Their presentation, ‘Hidden barriers to open competition: using text mining to uncover corrupt restrictions to competition in Public Procurement’, is related to Eszter’s PhD research.

Renáta Németh: Challenges of controlled machine learning in sociological applications

2022.01.24. Publication The layers of political public sphere in Hungary (2001–2020) Data Science in Social Research

One our researchers, Renáta Németh has gotten her paper published in the special issue of the journal Metszetek. Renáta examines the feature of controlled machine learning which requires human coding – touching upon ethical questions of crowdsourcing platforms, teachability of hermeneutically more complex terms, or the distortion of AI, the point of which is that the coders bring discrimination into data.

Ildikó Barna, Árpád Knap (2021): An exploration of coronavirus-related online antisemitism in Hungary using quantitative topic model and qualitative discourse analysis

2022.01.11. Publication Online Antisemitism
Soon after the outbreak of the pandemic, antisemitism connected to the coronavirus appeared in the world. Ildikó Barna and Árpád Knap, members of our group analyzed the Hungarian online public sphere using quantitative topic model complemented with qualitative text analysis. They also proposed a comprehensive typology of its coronavirus-related antisemitic content.

Németh, Renáta; Máté, Fanni; Katona, Eszter; Rakovics, Márton; Sik, Domonkos (2022): Bio, psycho, or social: supervised machine learning to classify discursive framing of depression in online health communities.

2022.01.08. Publication Discursive framing of depression in online health communities

Renáta Németh, Fanni Máté, Eszter Katona, Márton Rakovics and Domonkos Sik published their results in the journal Quality and Quantity: International Journal of Methodology with the following title: ” Bio, psycho, or social: supervised machine learning to classify discursive framing of depression in online health communities “.

Árpád Knap, Diána Bartha, Ildikó Barna (2021): Analysing The Memory Politics Of Trianon And The Holocaust Using Natural Language Processing

2022.01.04. Publication The layers of political public sphere in Hungary (2001–2020)

A new publication by members of our research team (Árpád Knap, Diána Bartha, Ildikó Barna) on the memory politics of Trianon and the Holocaust using NLP. Within the “European Memory Politics – Populism, Nationalism and the Challenges to a European Memory Culture (EuMePo)” international research network supported by Jean Monnet Network Grant. English abstract is also available on the link, and an English-language paper on this research is also in press.

Eszter Katona, Zoltán Kmetty, Renáta Németh (2021): Applying natural language processing to analyise the representation of corruption in the Hungarian online media

2021.07.19. Publication Corruption in Online Editorial Media

This paper presents a thematic analysis of the representation of corruption in the Hungarian online media, using a text mining tool called dynamic topic modeling. The text corpus was provided by K-Monitor and includes online articles on corruption and issues related to the misuse of public funds. Our study is exploratory in nature: it is aimed at identifying the main topics of the articles and the dynamics of thematic changes in the period 2007–2018, including the meaning, the background and the changes of each corruption topic. The causal links revealed by this research lie in whether the medium is of an oppositional or of a pro-government position, and how election campaign periods affect the thematic structure of the representation of corruption. Owing to the fact that the ownership of the news portal Origó changed during the analysed period, a natural experiment has also been possible in an attempt to reveal the impact of this change on the thematic structure of the corruption discourse on the portal in question.

https://mediakutato.hu/kiadvany/2021_02_nyar.html

Eszter Katona, Árpád Knap, Fanni Máté, Mihály Csótó – Topic modelling of the Információs Társadalom

2021.07.13. Publication

Three members of our research group: Eszter Katona, Árpád Knap and Fanni Máté, with the contribution of Mihály Csótó, wrote an article for the special anniversary issue of the Information Society journal. The primary aim of the study is to review the topics that the journal has included in the Hungarian discourse of “information society studies” over the past 15 years and to explore the thematic structure of the journal with NLP methods. In addition to the content analysis, the article also provides an insight into the co-author network of the journal, as well as the relationship between the authors and each topic.

The paper is accessible on the following URL: https://doi.org/10.22503/inftars.XXI.2021.1.1
The visualizations are available on this link: https://inftars.infonia.hu/inftars20?lang=hu

Fanni Máté (2021): Social Support on an Online Forum for Depression and Anxiety

2021.06.13. Publication Discursive framing of depression in online health communities

Nowadays, online communities are typical sources of social support, which is a considerable help especially for those suffering from depression or anxiety. The aim of my research is to investigate the patterns of social support on an online depression and anxiety forum and to serve as an exploratory research of Natural Language Processing usage to classify comments into the categories of social support. The uniqueness of my research is the quantitative text analysis based on a complete qualitative analysis of the whole dataset. The conclusions of the qualitative analysis provide profound information for model definition, and for their evaluation. This knowledge is important for the investigation the potential of automatic text analysis in sociology. On average, four out of five comments are related to social support on the examined forum. Informational support appears in 59.9 percent of the supportive comments, while emotional support appears in 44.7 percent. The applied models’ accuracies are nearly 80 percent, which means that they classified the vast majority of comments into the right category. The results show that there is a potential in building reliable models in order to classify the comments into the previously defined categories of social support.

https://szociologia.hu/szociologiai-szemle/tarsas-tamogatas-megjelenese-egy-depresszio-es-szorongas-temaju-online-forumon

Eszter Katona, Renáta Németh (2021): Automated text analytics in corruption research

2021.05.22. Publication Corruption in Online Editorial Media The layers of political public sphere in Hungary (2001–2020)
Our study examines the use and possible applicability of Natural Language Processing (NLP) in corruption research. In our review, we aim to collect and summarize automated text analytics-based corruption research born after 2000. We focus on the prevalence and potential of NLP methods. We found significant differences in the textual data sources, the corruption measurement methods, and the analytical approaches used.
However, there were unfortunately few mixed-type studies (in terms of data source, method, or corruption measurement method). In addition to the classic works describing of the volume of corruption or the attitude or perception related to it, we found results that can be used to prevent corruption and even be directly suitable for intervention. NLP has been used in only a few studies, and mostly only for some technical tasks. Our results show that NLP is not very widespread in this area yet. However, it can also be seen that its use can be useful and could support traditional quantitative research as an alternative tool. The aim of our article is to provide inspiration for the use of NLP in the social sciences and to draw attention to its embeddability in existing scientific discourses.

https://socio.hu/index.php/so/article/view/853