Beyond the Surface: Uncovering Implicit Locations with LLMs for Personalized Local News
It addresses the challenge of personalizing local news for users and newspapers, though it is incremental as it builds on existing methods like NER and Knowledge Graphs.
This paper tackled the problem of identifying local articles in news recommendation systems by using Large Language Models (LLMs) to detect implicit location cues, resulting in a 27% boost in local article distribution and increased local views in online tests.
News recommendation systems personalize homepage content to boost engagement, but factors like content type, editorial stance, and geographic focus impact recommendations. Local newspapers balance coverage across regions, yet identifying local articles is challenging due to implicit location cues like slang or landmarks. Traditional methods, such as Named Entity Recognition (NER) and Knowledge Graphs, infer locations, but Large Language Models (LLMs) offer new possibilities while raising concerns about accuracy and explainability. This paper explores LLMs for local article classification in Taboola's "Homepage For You" system, comparing them to traditional techniques. Key findings: (1) Knowledge Graphs enhance NER models' ability to detect implicit locations, (2) LLMs outperform traditional methods, and (3) LLMs can effectively identify local content without requiring Knowledge Graph integration. Offline evaluations showed LLMs excel at implicit location classification, while online A/B tests showed a significant increased in local views. A scalable pipeline integrating LLM-based location classification boosted local article distribution by 27%, preserving newspapers' brand identity and enhancing homepage personalization.