The evolution of political memes: Detecting and characterizing internet memes with multi-modal deep learning

Beskow, David M.; Kumar, Sumeet; Carley, Kathleen M.

doi:10.1016/j.ipm.2019.102170

Cited by 86 publications

(51 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In other words, memes offer new possibilities for parodying political parties and politicians and their ideological agendas (Piata, 2016, p. 40). Nonetheless, memes are sometimes racist (Williams et al, 2016); they resort to disparagement and even hate speech to spread political ideas, attack minorities, and exacerbate existing differences between political, social, and ideological extremes (Beskow et al, 2020). Denisova (2019) and Wiggins (2019) highlight the importance of specific socio-cultural factors.…”

Section: Introductionmentioning

confidence: 99%

From Polarization to Hate: Portrait of the Spanish Political Meme

Paz

Soria

González-Aguilar

2021

Social Media + Society

View full text Add to dashboard Cite

Political polarization in Spain has been aggravated by a left-wing coalition government and the rise of the extreme right in the context of health and economic crisis created by COVID-19. This article delves into the collective story that memes offer of this context and aims to establish a categorization that can be used for comparison with other countries. We carried out a content analysis of 636 Spanish political memes published on Twitter throughout 2020. Current affairs were taken into account, as well as the frame, and rhetorical elements, references to popular culture, and symbols. We also took into consideration the objectives of the message and the presence of offensive content. We demonstrate that these memes do not play a subversive role, but rather contribute to the polarization and fragmentation of the digital public, echoing the existing ideological confrontation. They do not deliver new ideas, but only reproduce expressions and disqualifications already existing in the society, although the disinhibition of anonymity magnifies the intensity. Current affairs are an excuse to convey ideological position, and political communication becomes more emotional. There are no significant differences in terms of political polarization between left and right, and criticism toward politicians is mainly of personal and moral nature. Hate speech on other social media appears in these cultural creations, highlighting the misogyny toward women politicians regardless of their political party. The rhetorical and expressive resources are adapted to this confrontation, and there is little innovation because it is subject to the understanding of the message.

show abstract

Section: Introductionmentioning

confidence: 99%

From Polarization to Hate: Portrait of the Spanish Political Meme

Paz

Soria

González-Aguilar

2021

Social Media + Society

View full text Add to dashboard Cite

show abstract

“…As shown by Beskow et al (2019), multimodal classifiers are considerably better than textual models and provide some improvement over unimodal vision models, which nevertheless provide solid performance in meme detection.…”

Section: Modelmentioning

confidence: 99%

UniBO @ AMI: A Multi-Class Approach to Misogyny and Aggressiveness Identification on Twitter Posts Using AlBERTo

Muti¹,

Barrón-Cedeño²

2020

EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020

View full text Add to dashboard Cite

Welcome to EVALITA 2020! EVALITA is the evaluation campaign of Natural Language Processing and Speech Tools for Italian. EVALITA is an initiative of the Italian Association for Computational Linguistics (AILC, http://www.ai-lc.it) and it is endorsed by the Italian Association for Artificial Intelligence (AIxIA, http://www.aixia.it) and the Italian Association for Speech Sciences (AISV, http://www.aisv.it).This volume includes the reports of both task organisers and participants to all of the EVALITA 2020 challenges. In the 2020 edition, we coordinated the organization of 14 different tasks belonging to five research areas, being: (i) Affect, Hate, and Stance, (ii) Creativity and Style, (iii) New Challenges in Long-standing Tasks, (iv) Semantics and Multimodality, Time and Diachrony.The volume is opened by an overview to the EVALITA 2020 campaign, in which we describe the tasks, provide statistics on the participants and task organizers as well as our supporting sponsors. The abstract of the keynote speech made by Preslav Nakov titled "Flattening the Curve of the COVID-19 Infodemic: These Evaluation Campaigns Can Help!" is also included in this collection.Due to the 2020 COVID-19 pandemic, the traditional workshop was held online, where several members of the Italian NLP Community presented the results of their research. Despite the circumstances, the workshop represented an occasion for all participants from both academic institutions and private companies to disseminate their work and results and to share ideas through online sessions dedicated to each task and a general discussion during the plenary event.We carried on with the tradition of the "Best system across tasks" award. As in 2018, it represented an incentive for students, IT developers and researchers to push the boundaries of the state of the art by facing tasks in new ways, even if not winning.

show abstract

“…The term of meme on the internet that we know today is an adaptation from what Richard Dawnkins said in his book but it has many fundamental differences in the definition behind memes on the internet. Memes on the internet are better known as words, emoticons, videos, or gifs, the most common forms are images with overlapping writing [3]. The current technological advances contribute to popularity of memes in internet [4], especially for millennials who are active users of social media.…”

Section: Introductionmentioning

confidence: 99%

Differences of Visual Attention to Memes: An Eye Tracking Study

Soleh¹,

Anisa²,

Absor³

et al. 2021

Advances in Social Science, Education and Humanities Research

View full text Add to dashboard Cite

Nowadays, memes are used as funny yet effective approach to send the messages for people. The growth of internet and digital media in recent years make memes easier to spread around the world. There are many studies about the perception to memes among different ages. However, it is still unclear the visual attention of people to memes. To solve the problem, human eye tracker could be used as objective and bias free technology. In this study, millennials and non-millennials participants were shown many memes image in random order. Participant's eye movements were recorded using human eye tracker to measure visual attention. Following eye tracking, participants completed a modified questionnaire to measure the perceptions of memes.

show abstract

The evolution of political memes: Detecting and characterizing internet memes with multi-modal deep learning

Cited by 86 publications

References 9 publications

From Polarization to Hate: Portrait of the Spanish Political Meme

From Polarization to Hate: Portrait of the Spanish Political Meme

UniBO @ AMI: A Multi-Class Approach to Misogyny and Aggressiveness Identification on Twitter Posts Using AlBERTo

Differences of Visual Attention to Memes: An Eye Tracking Study

Contact Info

Product

Resources

About