A fine-tuned large language model for improved click-bait title detection

dc.contributor.authorVuppala, Pavan Sai
dc.contributor.authorSekharan, Chandra N.
dc.date.accessioned2023-09-20T20:06:27Z
dc.date.available2023-09-20T20:06:27Z
dc.date.issued2023-08-29
dc.descriptionDepartment of Computing Sciences, College of Engineering
dc.description.abstractThe internet has experienced a widespread phenomenon of clickbait, especially on social media platforms and news websites. Clickbait headlines and descriptions attract clicks and generate ad revenue by using exaggerated, sensational, or misleading language. Clickbait can harm online users by wasting their time, spreading misinformation, damaging reputations, or even exposing them to malware or phishing attacks. Detecting clickbait manually is subjective and time-consuming since different people may have different opinions on what constitutes clickbait. Rule-based approaches, machine learning models[8], deep learning models[9] and natural language processing techniques are some of the existing methods for clickbait detection. However, clickbait detection remains a challenging task due to the diversity and complexity of clickbait content, as well as the constantly evolving strategies used by clickbait creators. In this research, we employed a methodology to detect clickbait titles using a fine-tuned large language model (LLM) that was trained on a limited dataset of clickbait titles.
dc.identifier.urihttps://hdl.handle.net/1969.6/97366
dc.language.isoen_US
dc.titleA fine-tuned large language model for improved click-bait title detection
dc.typePresentation

Files

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description: