Tharun Suresh

ORCID: 0000-0001-5280-9328
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Hate Speech and Cyberbullying Detection
  • Humor Studies and Applications
  • Misinformation and Its Impacts
  • Sentiment Analysis and Opinion Mining
  • Topic Modeling
  • Social Media and Politics
  • Natural Language Processing Techniques
  • Mental Health via Writing
  • Leadership, Courage, and Heroism Studies
  • Digital Mental Health Interventions
  • Speech and dialogue systems
  • Advanced Text Analysis Techniques
  • Text Readability and Simplification
  • Internet Traffic Analysis and Secure E-voting

Indraprastha Institute of Information Technology Delhi
2022-2024

Indian Institute of Technology Delhi
2022-2024

Shivam Sharma, Atharva Kulkarni, Tharun Suresh, Himanshi Mathur, Preslav Nakov, Md. Shad Akhtar, Tanmoy Chakraborty. Proceedings of the 17th Conference European Chapter Association for Computational Linguistics. 2023.

10.18653/v1/2023.eacl-main.157 article EN cc-by 2023-01-01

Shivam Sharma, Tharun Suresh, Atharva Kulkarni, Himanshi Mathur, Preslav Nakov, Md. Shad Akhtar, Tanmoy Chakraborty. Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations. 2022.

10.18653/v1/2022.constraint-1.1 article EN cc-by 2022-01-01

Being a popular mode of text-based communication in multilingual communities, code mixing online social media has become an important subject to study. Learning the semantics and morphology code-mixed language remains key challenge due scarcity data, unavailability robust, language-invariant representation learning techniques. Any morphologically rich can benefit from character, subword, word-level embeddings, aiding meaningful correlations. In this article, we explore hierarchical...

10.1109/tcss.2024.3360378 article EN IEEE Transactions on Computational Social Systems 2024-03-25

Memes are powerful means for effective communication on social media. Their effortless amalgamation of viral visuals and compelling messages can have far-reaching implications with proper marketing. Previous research memes has primarily focused characterizing their affective spectrum detecting whether the meme's message insinuates any intended harm, such as hate, offense, racism, etc. However, often use abstraction, which be elusive. Here, we introduce a novel task - EXCLAIM, generating...

10.1609/aaai.v37i8.26166 article EN Proceedings of the AAAI Conference on Artificial Intelligence 2023-06-26

The psychotherapy intervention technique is a multifaceted conversation between therapist and patient. Unlike general clinical discussions, psychotherapy's core components (viz. symptoms) are hard to distinguish, thus becoming complex problem summarize later. A structured counseling may contain discussions about symptoms, history of mental health issues, or the discovery patient's behavior. It also discussion filler words irrelevant summary. We refer these elements as components. In this...

10.1145/3534678.3539187 article EN Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2022-08-12

Memes can sway people's opinions over social media as they combine visual and textual information in an easy-to-consume manner. Since memes instantly turn viral, it becomes crucial to infer their intent potentially associated harmfulness take timely measures needed. A common problem with meme comprehension lies detecting the entities referenced characterizing role of each these entities. Here, we aim understand whether glorifies, vilifies, or victimizes entity refers to. To this end, address...

10.48550/arxiv.2301.11219 preprint EN cc-by-nc-sa arXiv (Cornell University) 2023-01-01

Being a popular mode of text-based communication in multilingual communities, code-mixing online social media has became an important subject to study. Learning the semantics and morphology code-mixed language remains key challenge, due scarcity data unavailability robust language-invariant representation learning technique. Any morphologically-rich can benefit from character, subword, word-level embeddings, aiding meaningful correlations. In this paper, we explore hierarchical...

10.48550/arxiv.2204.12753 preprint EN other-oa arXiv (Cornell University) 2022-01-01

Detecting online toxicity has always been a challenge due to its inherent subjectivity. Factors such as the context, geography, socio-political climate, and background of producers consumers posts play crucial role in determining if content can be flagged toxic. Adoption automated detection models production thus lead sidelining various groups they aim help first place. It piqued researchers' interest examining unintended biases their mitigation. Due nascent multi-faceted nature work,...

10.48550/arxiv.2202.00126 preprint EN other-oa arXiv (Cornell University) 2022-01-01

Tweets are the most concise form of communication in online social media, wherein a single tweet has potential to make or break discourse conversation. Online hate speech is more accessible than ever, and stifling its propagation utmost importance for media companies users congenial communication. Most research barring recent few focused on classifying an individual regardless thread/context leading up that point. One classical approaches curb adopt reactive strategy after postage. The...

10.48550/arxiv.2206.08406 preprint EN cc-by arXiv (Cornell University) 2022-01-01

Memes are powerful means for effective communication on social media. Their effortless amalgamation of viral visuals and compelling messages can have far-reaching implications with proper marketing. Previous research memes has primarily focused characterizing their affective spectrum detecting whether the meme's message insinuates any intended harm, such as hate, offense, racism, etc. However, often use abstraction, which be elusive. Here, we introduce a novel task - EXCLAIM, generating...

10.48550/arxiv.2212.00715 preprint EN cc-by-nc-sa arXiv (Cornell University) 2022-01-01

The psychotherapy intervention technique is a multifaceted conversation between therapist and patient. Unlike general clinical discussions, psychotherapy's core components (viz. symptoms) are hard to distinguish, thus becoming complex problem summarize later. A structured counseling may contain discussions about symptoms, history of mental health issues, or the discovery patient's behavior. It also discussion filler words irrelevant summary. We refer these elements as components. In this...

10.48550/arxiv.2206.03886 preprint EN cc-by arXiv (Cornell University) 2022-01-01
Coming Soon ...