Towards an NLP-Based Topic Characterization of Social Relations

Hauffa, Jan; Lichtenberg, Tobias; Groh, Georg

doi:10.1109/socialinformatics.2012.80

Cited by 5 publications

(2 citation statements)

References 13 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used two different NLP methods: (1) With TextRank (Mihalcea & Tarau, 2004), we extracted keywords that best summarize a document. This method has previously been used to study social relations showing that keywords capture more than just superficial topics in a text corpus (Hauffa et al, 2012). Subsequently, we conducted a thematic analysis of these keywords to describe similarity and dissimilarity patterns across time and newspapers, and to provide a thematic summary of the corpus of articles per newspaper.…”

Section: Analysis Strategymentioning

confidence: 99%

What holds society together? Tracking moral courage across 75 years and three democratic societies

Schalk¹,

Fischer²,

Luczak‐Roesch³

2023

Preprint

View full text Add to dashboard Cite

Moral courage – standing up and out in defense of personal and moral principles – is crucial for societies and may counteract rising challenges to democracy. Yet, what is moral courage? Is there a stable core of features that are invariant across time and cultures? We used natural language processing and human coding to analyze 2,328 articles across 75 years in newspapers-of-record in three major democracies (USA, UK, Germany). German newspapers emphasized acts by ordinary citizens to uphold democratic values, whereas in English the focus was on politicians and personal values, which may also be anti-democratic. Temporal changes were linked to localized events, with relatively few persistent longer-term shifts. Our results provide insights to why encouraging moral courage may have divergent implications for social institutions in English-vs German-speaking contexts and highlight the importance of examining the generalisability of psychological constructs across languages and cultures.

show abstract

Section: Analysis Strategymentioning

confidence: 99%

What holds society together? Tracking moral courage across 75 years and three democratic societies

Schalk¹,

Fischer²,

Luczak‐Roesch³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We used two different NLP methods: (1) With TextRank (Mihalcea & Tarau, 2004), we extracted keywords that best summarize a document. This method has previously been used to study social relations showing that keywords capture more than just superficial topics in a text corpus (Hauffa et al, 2012). Subsequently, we describe similarity and dissimilarity patterns of the extracted keywords across time to gain broad insights into possible temporal developments of topics within articles.…”

mentioning

confidence: 99%

240 Years of Public Discourse on Moral Courage in The London Times

Schalk,

Fischer,

Luczak-Roesch

2024

Preprint

View full text Add to dashboard Cite

Rising right-wing influences and hate crime threaten the livelihoods of significant segments of multicultural societies. Moral courage and its variations (e.g., in German Zivilcourage) can contribute to stopping such developments and keep society peaceful and cohesive. Current studies have focused on the understanding and, for example, determinants of these concepts in today’s societies. However, little is known about the evolution of the concept and associated discourses over longer periods. In this study we trace the evolution of the term moral courage over a period of more than two hundred years in the UK to examine whether and how this concept may have played a role in public discourse during past crises. We use state-of-the-art natural language processing methods to analyse 2646 newspaper articles from The Times. Moral courage was mainly connected to political topics, such as the military, domestic affairs, and foreign affairs. This contrasts with most definitions of moral courage in psychological and sociological studies. This divide between the public understanding of moral courage and the academic definitions can lead to flawed studies when not considering participant’s understanding of the concept and presents problems in communicating results that may help to counter discrimination and increase cooperation in society.

show abstract

Keyword Extraction for Medium‐Sized Documents Using Corpus‐Based Contextual Semantic Smoothing

et al. 2022

View full text Add to dashboard Cite

Keyword extraction refers to the process of selecting most significant, relevant, and descriptive terms as keywords, which are present inside a single document. Keyword extraction has major applications in the information retrieval domain, such as analysis, summarization, indexing, and search, of documents. In this paper, we present a novel supervised technique for extraction of keywords from medium-sized documents, namely Corpus-based Contextual Semantic Smoothing (CCSS). CCSS extends the concept of Contextual Semantic Smoothing (CSS), which considers term usage patterns in similar texts to improve term relevance information. We introduce four more features beyond CSS as our novel contributions in this work. We systematically compare the performance of CCSS with other techniques, when implemented over INSPEC dataset, where CCSS outperforms all state-of-the-art keyphrase extraction techniques presented in the literature.

show abstract

Towards an NLP-Based Topic Characterization of Social Relations

Cited by 5 publications

References 13 publications

What holds society together? Tracking moral courage across 75 years and three democratic societies

What holds society together? Tracking moral courage across 75 years and three democratic societies

240 Years of Public Discourse on Moral Courage in The London Times

Keyword Extraction for Medium‐Sized Documents Using Corpus‐Based Contextual Semantic Smoothing

Contact Info

Product

Resources

About