Challenges and Opportunities of Text-Based Emotion Detection: A Survey

IEEE Access, Год журнала: 2024, Номер 12, С. 18416 - 18450

Опубликована: Янв. 1, 2024

Emotion detection has become an intriguing issue for researchers because of its psychological, social, and commercial significance. People express their feelings directly or indirectly through facial expressions, language, writing, behavior. An emotion tool is a critical practical way recognizing categorizing moods with various applications. Artificial intelligence often used in research to identify emotions. Machine learning deep algorithms produce high-quality solutions diagnosing emotional diseases social media users. Numerous studies survey articles have been published on based textual data. However, most these did not comprehensively address emerging architectures performance analysis detection. This paper provides extensive state-of-the-art systems, techniques, datasets recognition. Another goal this study emphasize the limitations provide up-and-coming directions fill gaps rapidly evolving field. investigated concepts performances different categories models, approaches, methodologies.

Язык: Английский

---

The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 467 - 478

Опубликована: Янв. 1, 2025

Язык: Английский

---

Detecting Propaganda Techniques in Code-Switched Social Media Text

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Год журнала: 2023, Номер unknown, С. 16794 - 16812

Опубликована: Янв. 1, 2023

Propaganda is a form of communication intended to influence the opinions and mindset public promote particular agenda. With rise social media, propaganda has spread rapidly, leading need for automatic detection systems. Most work on focused high-resource languages, such as English, little effort been made detect low-resource languages. Yet, it common find mix multiple languages in media communication, phenomenon known code-switching. Code-switching combines different within same text, which poses challenge Considering this premise, we propose novel task detecting techniques code-switched text. To support task, create corpus 1,030 texts code-switching between English Roman Urdu, annotated with 20 at fragment-level. We perform number experiments contrasting experimental setups, that important model multilinguality directly rather than using translation well use right fine-tuning strategy. plan publicly release our code dataset.

Язык: Английский

---

Unveiling Deception in Arabic: Optimization of Deceptive Text Detection Across Formal and Informal Genres

IEEE Access, Год журнала: 2024, Номер 12, С. 94216 - 94230

Опубликована: Янв. 1, 2024

In recent years, social media has significantly influenced how we share information and exchange messages. However, a significant issue arises from the fast dissemination of deceptive portrayed as legitimate, which may seriously affect both people society. Identifying unmonitored 'deceptive text' become crucial concern in mainstream due to its potentially damaging impact. Although there have been studies that developed AI models capable identifying text other languages, is scarcity research focused on detecting detective specifically Arabic language. This paper presents novel detection dataset constructed publicly available resources. The offers unique distinction between formal informal genres, reflecting diverse communication styles encountered real-world We evaluate performance various machine learning (ML), deep (DL), transformer-based this for classifying or non-deceptive. study investigates impact incorporating additional textual features including morphological features, psycholinguistic sociolinguistic alongside raw data. Our findings demonstrate AraBERTv2 model, after fine-tuning achieves best classification performance. contributes valuable resource analysis highlights effectiveness fine-tuned with enriched such tasks.

Язык: Английский

---

Nexus at ArAIEval Shared Task: Fine-Tuning Arabic Language Models for Propaganda and Disinformation Detection

Опубликована: Янв. 1, 2023

The spread of disinformation and propagandistic content poses a threat to societal harmony, undermining informed decision-making trust in reliable sources. Online platforms often serve as breeding grounds for such content, malicious actors exploit the vulnerabilities audiences shape public opinion. Although there have been research efforts aimed at automatic identification propaganda social media remain challenges terms performance. ArAIEval shared task aims further on these particular issues within context Arabic language. In this paper, we discuss our participation tasks. We competed subtasks 1A 2A, where submitted system secured positions 9th 10th, respectively. Our experiments consist fine-tuning transformer models using zero- few-shot learning with GPT-4.

Язык: Английский

---

USTHB at ArAIEval’23 Shared Task: Disinformation Detection System based on Linguistic Feature Concatenation

Опубликована: Янв. 1, 2023

In this research paper, we undertake a comprehensive examination of several pivotal factors that impact the performance Arabic Disinformation Detection in ArAIEval’2023 shared task. Our exploration encompasses influence surface preprocessing, morphological FastText vector model, and weighted fusion TF-IDF features. To carry out classification tasks, employ Linear Support Vector Classification (LSVC) model. evaluation phase, our system showcases significant results, achieving an F1 micro score 76.70% 50.46% for binary multiple scenarios, respectively. These accomplishments closely correspond to average scores achieved by other systems submitted second subtask, standing at 77.96% 64.85%

Язык: Английский

---

Itri Amigos at ArAIEval Shared Task: Transformer vs. Compression-Based Models for Persuasion Techniques and Disinformation Detection

Опубликована: Янв. 1, 2023

Social media has significantly amplified the dissemination of misinformation. Researchers have employed natural language processing and machine learning techniques to identify categorize false information on these platforms. While there is a well-established body research detecting fake news in English Latin languages, study Arabic detection remains limited. This paper describes methods used tackle challenges ArAIEval shared Task 2023. We conducted experiments with both monolingual multi-lingual pre-trained Language Models (LM). found that models outperformed all four subtasks. Additionally, we explored novel lossless compression method, which, while not surpassing pretrained LM performance, presents an intriguing avenue for future experimentation achieve comparable results more efficient rapid manner.

Язык: Английский

---

ReDASPersuasion at ArAIEval Shared Task: Multilingual and Monolingual Models For Arabic Persuasion Detection

Опубликована: Янв. 1, 2023

To enhance persuasion detection, we investigate the use of multilingual systems on Arabic data by conducting a total 22 experiments using baselines, multilingual, and monolingual language transformers. Our aim is to provide comprehensive evaluation various employed throughout this task, with ultimate goal comparing their performance identifying most effective approach. empirical analysis shows that *ReDASPersuasion* system performs best when combined “XLM-RoBERTa” pre-trained transformers dialects like “CAMeLBERT-DA SA” depending NLP classification task.

Язык: Английский

---

AraDetector at ArAIEval Shared Task: An Ensemble of Arabic-specific pre-trained BERT and GPT-4 for Arabic Disinformation Detection

Опубликована: Янв. 1, 2023

The rapid proliferation of disinformation through social media has become one the most dangerous means to deceive and influence people’s thoughts, viewpoints, or behaviors due media’s facilities, such as access, lower cost, ease use. Disinformation can spread in different ways, fake news stories, doctored images videos, deceptive data, even conspiracy theories, thus making detecting challenging. This paper is a part participation ArAIEval competition that relates detection. work evaluated four models: MARBERT, proposed ensemble model, two tests over GPT-4 (zero-shot Few-shot). achieved micro-F1 79.01% while method obtained 76.83%. Despite no improvement score on dev dataset using approach, we still used it for test predictions. We believed merging classifiers might enhance system’s prediction accuracy.

Язык: Английский

---

Raphael at ArAIEval Shared Task: Understanding Persuasive Language and Tone, an LLM Approach

Опубликована: Янв. 1, 2023

The widespread dissemination of propaganda and disinformation on both social media mainstream platforms has become an urgent concern, attracting the interest various stakeholders such as government bodies companies. challenge intensifies when dealing with understudied languages like Arabic. In this paper, we outline our approach for detecting persuasion techniques in Arabic tweets news article paragraphs. We submitted system to ArAIEval 2023 Shared Task 1, covering subtasks. Our main contributions include utilizing GPT-3 discern tone potential text, exploring base language models, employing a multi-task learning specified

Язык: Английский

---