SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images

Dimitrov, Dimitar; Ali, Bishr Bin; Shaar, Shaden; Alam, Firoj; Silvestri, Fabrizio; Firooz, Hamed; Nakov, Preslav; Martino, Giovanni Da San

doi:10.18653/v1/2021.semeval-1.7

Cited by 45 publications

(44 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Certain types of ad hominem attacks are relatively easy to detect, especially attacks in which other indicators feature, such as slurs and stereotypical language. The existing datasets that contain name calling or smears as a type of ad hominem reflect this [63,64]. But there are contextsensitive ad hominem attacks whose detection requires a natural language understanding level not yet achieved by current systems.…”

Section: Practical Implicationsmentioning

confidence: 99%

“…Despite the existing research, automatic irony or sarcasm detection or automatic detection of a manipulative style or misinterpretations is still far from a solved problem. Although there are labeled datasets on irony [65], humor [66], and manipulative (propaganda) techniques [63,64], the current systems do not possess a level of natural language understanding that would enable them to reliably detect such phenomena. Yet our analysis shows that the use of ambigu-Table 2 Map of proposed indicators to existing NLP datasets on hate speech and related phenomena, such as offensive and abusive language and the assessment of the current level of readiness for the automatic detection of each indicator given the availability of data and the capability of existing approaches…”

Section: Practical Implicationsmentioning

confidence: 99%

See 1 more Smart Citation

Hate speech operationalization: a preliminary examination of hate speech indicators and their structure

Papcunová

Martončik

Fedáková

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Hate speech should be tackled and prosecuted based on how it is operationalized. However, the existing theoretical definitions of hate speech are not sufficiently fleshed out or easily operable. To overcome this inadequacy, and with the help of interdisciplinary experts, we propose an empirical definition of hate speech by providing a list of 10 hate speech indicators and the rationale behind them (the indicators refer to specific, observable, and measurable characteristics that offer a practical definition of hate speech). A preliminary exploratory examination of the structure of hate speech, with the focus on comments related to migrants (one of the most reported grounds of hate speech), revealed that two indicators in particular, denial of human rights and promoting violent behavior, occupy a central role in the network of indicators. Furthermore, we discuss the practical implications of the proposed hate speech indicators—especially (semi-)automatic detection using the latest natural language processing (NLP) and machine learning (ML) methods. Having a set of quantifiable indicators could benefit researchers, human right activists, educators, analysts, and regulators by providing them with a pragmatic approach to hate speech assessment and detection.

show abstract

Section: Practical Implicationsmentioning

confidence: 99%

Section: Practical Implicationsmentioning

confidence: 99%

Hate speech operationalization: a preliminary examination of hate speech indicators and their structure

Papcunová

Martončik

Fedáková

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…We further plan to develop new multi-modal models, specifically tailored to fine-grained propaganda detection, aiming for deeper understanding of the semantics of the meme and of the relation between the text and the image. A number of promising ideas have been already tried by the participants in a shared task based on this data at SemEval-2021 (Dimitrov et al, 2021), which can serve as an inspiration when developing new models.…”

Section: Discussionmentioning

confidence: 99%

Detecting Propaganda Techniques in Memes

Dimitrov¹,

Ali²,

Shaar³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Propaganda can be defined as a form of communication that aims to influence the opinions or the actions of people towards a specific goal; this is achieved by means of well-defined rhetorical and psychological devices. Propaganda, in the form we know it today, can be dated back to the beginning of the 17th century. However, it is with the advent of the Internet and the social media that it has started to spread on a much larger scale than before, thus becoming major societal and political issue. Nowadays, a large fraction of propaganda in social media is multimodal, mixing textual with visual content. With this in mind, here we propose a new multi-label multimodal task: detecting the type of propaganda techniques used in memes. We further create and release a new corpus of 950 memes, carefully annotated with 22 propaganda techniques, which can appear in the text, in the image, or in both. Our analysis of the corpus shows that understanding both modalities together is essential for detecting these techniques. This is further confirmed in our experiments with several state-of-the-art multimodal models.

show abstract

“…The dataset consists of 951 memes in total, which is further divided into train/ The distribution of the labels is illustrated in figure 2. Detailed information of the dataset can be found in the task description paper (Dimitrov et al, 2021).…”

Section: Data Descriptionmentioning

confidence: 99%

“…To this end, SemEval 2021 Task 6 (Dimitrov et al, 2021) focuses on identifying such persuasive techniques (Miller, 1939) in a multimodal (visuallinguistic) setting. It consists of three subtasks that enable the participants to study the problem in each modality.…”

Section: Introductionmentioning

confidence: 99%

Volta at SemEval-2021 Task 6: Towards Detecting Persuasive Texts and Images using Textual and Multimodal Ensemble

Gupta¹,

Gautam²,

Mamidi³

2021

Preprint

View full text Add to dashboard Cite

Memes are one of the most popular types of content used to spread information online. They can influence a large number of people through rhetorical and psychological techniques. The task, Detection of Persuasion Techniques in Texts and Images, is to detect these persuasive techniques in memes. It consists of three subtasks: (A) Multi-label classification using textual content, (B) Multi-label classification and span identification using textual content, and (C) Multi-label classification using visual and textual content. In this paper, we propose a transfer learning approach to fine-tune BERT-based models in different modalities. We also explore the effectiveness of ensembles of models trained in different modalities. We achieve an F1-score of 57.0, 48.2, and 52.1 in the corresponding subtasks.

show abstract

SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images

Cited by 45 publications

References 35 publications

Hate speech operationalization: a preliminary examination of hate speech indicators and their structure

Hate speech operationalization: a preliminary examination of hate speech indicators and their structure

Detecting Propaganda Techniques in Memes

Volta at SemEval-2021 Task 6: Towards Detecting Persuasive Texts and Images using Textual and Multimodal Ensemble

Contact Info

Product

Resources

About