Paper accepted to appear @ NLP4PI, EMNLP2024, Covert Bias: The Severity of Social Views’ Unalignment in Language Models Towards Implicit and Explicit Opinion,Abeer Aldayel, Areej Alokaili, Rehab Alahmadi
New pre-print! Covert Bias: The Severity of Social Views’ Unalignment in Language Models Towards Implicit and Explicit Opinion, (Abeer Aldayel, Areej Alokaili, Rehab Alahmadi), under-review, preprint(link)
Paper accepted to appear @ ICWSM, Hatred Stems from Ignorance! Distillation of the Persuasion Modes in Countering Conversational Hate Speech, (Ghadi Alyahya, Abeer Aldayel), ICWSM2025, preprint(link)
Gave a talk @ Saudi Digital Academy for Data Science, "Efficacy of Social Aspect and Human-Centered Paradigm From Real-World Scenarios to LLM", SDA academy
New pre-print! Hatred Stems from Ignorance! Distillation of the Persuasion Modes in Countering Conversational Hate Speech.(under-review), (Ghadi Alyahya, Abeer Aldayel), preprint(link)
Co-organized the Data Challenge,ICWSM, Temporal Data
Gave a talk @ SDAIA Academy, Computational Social Science For NLP: Closer Look at Reliability through Feedback & Human-Centered Values, arranged by AI Center of Advanced Studies Thakaa
Paper accepted @NEATCLASS ICWSM, Toxicity Inspector: A Framework to Evaluate Ground Truth in Toxicity Detection Through Feedback
Our graduation project team selected for digital innovation award "Toxicity inspector: Multilingual toxic comments mitigation through feedback"
Our paper "Characterizing the role of bots’ in polarized stance on social media" got accepted at SNAM
Gave a talk @women_in_nlp "Social computing through the lens of NLP: a closer look at opportunities, reliability and beyond"
Starting new position as assistant professor at King Saud University
Received the Best Reviewer Award in ICWSM 2021
Passed my PhD viva , starting my job @ KSU as assistant professor soon
Our paper "Stance detection on social media: state-of-the-art and trends" got accepted at IP&M
Presented recent work on stance polarization on social media at IC2S2-2020.
Received the Best Reviewer Award in ICWSM 2020.
Our tutorial "Detection and Characterization of Stance on Social Media" Accepted @ICWSM 2020
Our paper "Assessing Sentiment of the Expressed Stance on Social Media" Accepted @SocInfo2019
IC2S2 submission has been accepted, It is more than what you Say! Leveraging User Online Activity for Improved Stance Detection
Our paper "Similar Minds Post Alike: Assessment of Suicide Risk by Hybrid Language and Behavioral Model" Accepted @CLPsych2019
Our paper "ARC-WMI" Accepted @OSACT3
Our paper "Readability of WMIs" published @ BMC health services research Journal
- About me and my research interest:
I am an assistant professor at the College of Computer and Information Sciences, King Saud University. My research interests lie primarily in Computational Social Science and Natural Language Processing . Most generally, I am working on NLP models and computational methods to recognize social aspects of language and modeling the use of language in social contexts to understand different phenomena with focus on multilingual/social processing, such as tackling biases, abusive language, and misinformation.
[I am not interested in monolingual or polyglossia/dialects, aka. Arabic-NLP/Social Network or Religious studies/ Healthcare/political analysis/ privacy applications/ policy or Cybersecurity or startups! please check FAQ page and my most recent research !]
- Highlights of my research so far :
♦ Computational Social Science and Natural Language Processing
Social Bias (social views and cultural aspect alignment [Multilingual]), Hate speech (reliability evaluation, counter-speech), Stance detection, Suicide level assessment.
♦ Natural Language Processing
Cross-lingual paraphrasing techniques, Readability assessment, Rumours veracity detection.
- More about my most recent research at this page.
I got my Ph.D. in (August 2021) from the University of Edinburgh, the Institute for Language, Cognition and Communication (ILCC) at School of Informatics
, as a member of (SMASH) research group. In my Ph.D. thesis, I worked on assessing the social factors of the stance in social media, where I worked in evaluating the effectiveness of
sentiment along with different interactions signals in detecting the stance in social media by using the SemEval 2016 stance dataset along with extended context-based stance dataset.
Also, the thesis proposed a framework for responsible stance detection, in addition to assess the stance of bots generated posts and humans posts in social computing setting.
Moreover, during my Ph.D. I had a chance to work on two side projects; in the first one, we developed a hybrid language model and behaviour model to assess suicide risk (CLPsych workshop@ NAACL2019).
The second project focused on rumors veracity detection, where I worked on the conversation level (replies set) of a given post.
Before starting my PhD, I earned a BSc and MSc in Computer and Information Sciences from King Saud University (KSU). In my Master thesis, I worked on developing query paraphrasing algorithm to enhance information retrieval system. Beside my job as lecturer at (KSU),
I worked as a research assistant in a readability identification project to predict the readability level of a given text. 📚 My personal interests include learning different languages, and reading [recommend me a book for my reading list here :) ]📚