Beyond the Surface: Uncovering Implicit Locations with LLMs for Personalized Local News

TL;DR

This paper investigates the use of Large Language Models to identify implicit locations in local news articles, improving personalization and increasing local content distribution in news recommendation systems.

Contribution

It demonstrates that LLMs outperform traditional methods in classifying implicit locations and can be integrated into scalable pipelines for better news personalization.

Findings

LLMs outperform traditional location inference methods.

Knowledge Graphs improve NER models for implicit location detection.

LLMs increase local article views and distribution by 27%.

Abstract

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.