Hashtags, Emotions, and Comments: A Large-Scale Dataset to Understand Fine-Grained Social Emotions to Online Topics

Ding, Keyang; Li, Jing; Zhang, Yuji

doi:10.18653/v1/2020.emnlp-main.106

“…Meist werden einzelne Aspekte wie Emotionen (vgl. Ding et al 2020;Tong 2015) oder Gegenöffentlichkeiten (vgl. Freudenthaler 2020; Toepfl und Piwoni 2018) analysiert, oder es handelt sich um theoretische Beiträge mit entsprechend großer Flughöhe (vgl.…”

Section: Abstract Agonism • Public • Online Communication • Instrumen...unclassified

Agonistische Online-Öffentlichkeiten

Frieß

¹

,

Gilleßen

²

2022

Publizistik

2

0

View full text Add to dashboard Cite

ZusammenfassungDas Internet hat die Möglichkeiten zur Konfliktaustragung radikal verändert. Insbesondere soziale Medien eröffnen agonistische Arenen, in denen konträre Positionen aufeinanderprallen. Obgleich die theoretische Konzeption des Internets als agonistische Sphäre nicht neu ist, liegen bisher kaum inhaltsanalytische Instrumente vor, die eine ganzheitliche Betrachtung agonistischer Diskursstrukturen ermöglichen. Der Beitrag will diese Lücke schließen, indem er einen Vorschlag zur Operationalisierung von Agonismus unterbreitet. Er wirbt damit gleichsam für einen Perspektivenwechsel bei der Analyse politischer Online-Kommunikation vor dem Hintergrund aktueller Debatten zu digitalen Öffentlichkeiten. Während deliberative Theorien von einem verständigungsorientierten Kommunikationsmodus ausgehen, an dessen Ende prinzipiell eine Form von Konsens möglich ist, stehen im Agonismus Konflikt, Gegnerschaft, Hegemonie, kollektive Identitäten und Leidenschaften im Vordergrund. Vor dem Hintergrund der Arbeiten von Chantal Mouffe arbeitet der Beitrag diese theoretischen Dimensionen heraus. Mit Blick auf bisherige Online-Kommunikationsforschung wird argumentiert, dass das Internet vielerorts agonistische Kommunikationsräume eröffnet, die es weiter zu analysieren gilt. Daran anschließend wird eine inhaltsanalytische Operationalisierung vorgeschlagen und im Rahmen einer Fallstudie illustriert. Die Ergebnisse einer Inhaltanalyse von 945 Nutzerkommentaren auf den Facebook-Seiten der im Bundestag vertretenen Parteien zeigen, dass das vorgeschlagene Instrument geeignet ist, um agonistische Diskursstrukturen zu identifizieren und zu analysieren. Der Beitrag diskutiert abschließend das vorgestellte Instrument und skizziert eine agonistische Forschungsagenda, wobei die Deliberationsforschung als Inspiration genutzt wird.

show abstract

“…In NLP, annotating and classifying text (in social media) for sentiment or emotions is a wellestablished task (Demszky et al, 2020;Ding et al, 2020;Haider et al, 2020;Hutto and Gilbert, 2014;Oberländer and Klinger, 2018). Importantly, our approach focuses on expressions of (anti-)solidarity: For example, texts containing a positive sentiment towards persons, groups or organizations which are at their core anti-European, nationalistic and excluding reflect anti-solidarity and are annotated as such.…”

Section: Emotion and Sentiment Classification In Nlpmentioning

confidence: 99%

Changes in European Solidarity Before and During COVID-19: Evidence from a Large Crowd- and Expert-Annotated Twitter Dataset

Ils¹,

Liú²,

Grunow³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

We introduce the well-established social scientific concept of social solidarity and its contestation, anti-solidarity, as a new problem setting to supervised machine learning in NLP to assess how European solidarity discourses changed before and after the COVID-19 outbreak was declared a global pandemic. To this end, we annotate 2.3k English and German tweets for (anti-)solidarity expressions, utilizing multiple human annotators and two annotation approaches (experts vs. crowds). We use these annotations to train a BERT model with multiple data augmentation strategies. Our augmented BERT model that combines both expert and crowd annotations outperforms the baseline BERT classifier trained with expert annotations only by over 25 points, from 58% macro-F1 to almost 85%. We use this highquality model to automatically label over 270k tweets between September 2019 and December 2020. We then assess the automatically labeled data for how statements related to European (anti-)solidarity discourses developed over time and in relation to one another, before and during the COVID-19 crisis. Our results show that solidarity became increasingly salient and contested during the crisis. While the number of solidarity tweets remained on a higher level and dominated the discourse in the scrutinized time frame, anti-solidarity tweets initially spiked, then decreased to (almost) pre-COVID-19 values before rising to a stable higher level until the end of 2020.

show abstract

“…Emotion and Sentiment Classification in NLP. In NLP, annotating and classifying text (in social media) for sentiment or emotions is a wellestablished task (Demszky et al, 2020;Ding et al, 2020;Haider et al, 2020;Hutto and Gilbert, 2014;Oberländer and Klinger, 2018). Importantly, our approach focuses on expressions of (anti-)solidarity: For example, texts containing a positive sentiment towards persons, groups or organizations which are at their core anti-European, nationalistic and excluding reflect anti-solidarity and are annotated as such.…”

Section: Related Workmentioning

confidence: 99%

Changes in European Solidarity Before and During COVID-19: Evidence from a Large Crowd- and Expert-Annotated Twitter Dataset

Ils¹,

Liú²,

Grunow³

et al. 2021

Preprint

0

View full text Add to dashboard Cite

We introduce the well-established social scientific concept of social solidarity and its contestation, anti-solidarity, as a new problem setting to supervised machine learning in NLP to assess how European solidarity discourses changed before and after the COVID-19 outbreak was declared a global pandemic. To this end, we annotate 2.3k English and German tweets for (anti-)solidarity expressions, utilizing multiple human annotators and two annotation approaches (experts vs. crowds). We use these annotations to train a BERT model with multiple data augmentation strategies. Our augmented BERT model that combines both expert and crowd annotations outperforms the baseline BERT classifier trained with expert annotations only by over 25 points, from 58% macro-F1 to almost 85%. We use this highquality model to automatically label over 270k tweets between September 2019 and December 2020. We then assess the automatically labeled data for how statements related to European (anti-)solidarity discourses developed over time and in relation to one another, before and during the COVID-19 crisis. Our results show that solidarity became increasingly salient and contested during the crisis. While the number of solidarity tweets remained on a higher level and dominated the discourse in the scrutinized time frame, anti-solidarity tweets initially spiked, then decreased to (almost) pre-COVID-19 values before rising to a stable higher level until the end of 2020.

show abstract

Hashtags, Emotions, and Comments: A Large-Scale Dataset to Understand Fine-Grained Social Emotions to Online Topics

Cited by 11 publications

References 22 publications

Agonistische Online-Öffentlichkeiten

Agonistische Online-Öffentlichkeiten

Changes in European Solidarity Before and During COVID-19: Evidence from a Large Crowd- and Expert-Annotated Twitter Dataset

Changes in European Solidarity Before and During COVID-19: Evidence from a Large Crowd- and Expert-Annotated Twitter Dataset

Contact Info

Product

Resources

About