Sarcasm Detection in Tunisian Social Media Comments: Case of COVID-19

Mekki, Asma; Zribi, Inès; Ellouze, Mariem; Belguith, Lamia Hadrich

doi:10.1007/978-3-031-16564-1_5

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Arabic online humour is investigated in terms of computational linguistics [Mekki et al 2022], communication studies including the gender and age aspects [Haider and Abbas 2022;Lesmana 2021;Banikalef et al 2014], and so on. However, the language of social media humour as a means of national self-identification requires a more in-depth analysis.…”

Section: Humour As a Means Of National Self-expressionmentioning

confidence: 99%

Arab National Identity in Online Humour: Sociolinguistic Perspective

Kucherenko

2023

Shìdnij svìt

View full text Add to dashboard Cite

This paper deals with the peculiarities of language code choice as a means of national selfexpression in the Arabic social media humour (in particular, in memes and jokes). In the globa-lized online communities, humour can play a pivotal role for the rapprochement of in-group mem-bers based on a certain type of their identity (national, social, gender, etc.). In this study, the notion of Arab national identity refers to the entire Ummah and, on the other hand, to the representatives of different Arab countries as well. It is reflected on the Arabic language variation online and beyond. This research revealed diverse language attitudes conveyed within the "selfother" binary opposition. The analysis of over 1,000 online posts (Egyptian, Iraqi, Moroccan, and other) showed that the commonality with the in-group members is expressed with the language code which is considered the closest for the recipients. It is indicated to the predominance of colloquial varieties (territorial dialects, sociolects, youth slang) with the variation in their written transmission. Modern Standard Arabic is used as well, sometimes with minor deviations from the norm or with the colloquial lexis insertions. Both explicit and implicit lexical tools (colloquial and slang words, precedent lexis, etc.) are utilized to stress the uniqueness of "self". Different codes are used to create the contrast between "self" (all Arabs / a certain Arab country) and "other" (all non-Arabs / the West / a certain Arab or non-Arab country, etc.). The studied varieties were also affected by the sociocultural context, topics of posts, communicants' situational roles, the technology, and so forth. The results of this investigation ascertained that the Arabic language form used in the humorous posts is an integral part of the communicants' identity as it demonstrates their belonging to a national group with its specific sociocultural, political, and historical background.

show abstract

Section: Humour As a Means Of National Self-expressionmentioning

confidence: 99%

Arab National Identity in Online Humour: Sociolinguistic Perspective

Kucherenko

2023

Shìdnij svìt

View full text Add to dashboard Cite

show abstract

Tokenization of Tunisian Arabic: A Comparison between Three Machine Learning Models

Mekki

Zribi

Ellouze

et al. 2023

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

Tokenization represents the way of segmenting a piece of text into smaller units called tokens. Since Arabic is an agglutinating language by nature, this treatment becomes a crucial preprocessing step for many Natural Language Processing (NLP) applications such as morphological analysis, parsing, machine translation, information extraction, etc. In this paper, we investigate word tokenization task with a rewriting process to rewrite the orthography of the stem. For this task, we are using Tunisian Arabic (TA) text. To the best of the researchers’ knowledge, this is the first study that uses Tunisian Arabic for word tokenization. Therefore, we start by collecting and preparing various TA corpora from different sources. Then, we present a comparison of three character-based tokenizers based on Conditional Random Fields (CRF), Support Vector Machines (SVM) and Deep Neural Networks (DNN). The best proposed model using CRF achieved an F-measure result of 88.9%.

show abstract

Sarcasm Detection in Tunisian Social Media Comments: Case of COVID-19

Cited by 2 publications

References 12 publications

Arab National Identity in Online Humour: Sociolinguistic Perspective

Arab National Identity in Online Humour: Sociolinguistic Perspective

Tokenization of Tunisian Arabic: A Comparison between Three Machine Learning Models

Contact Info

Product

Resources

About