Local Life: Stay Informed Around You, A Scalable Geoparsing and Geotagging Approach to Serve Local News Worldwide

TL;DR

This paper presents a scalable approach for geolocating local news articles and determining their influence scope to improve hyperlocal news delivery worldwide.

Contribution

It introduces a novel method for geolocation and influence scope detection, enhancing local news recommendation systems.

Findings

Effective geolocation of local news articles

Scalable approach suitable for worldwide deployment

Improved accuracy in local news influence estimation

Abstract

Local news has become increasingly important in the news industry due to its various benefits. It offers local audiences information that helps them participate in their communities and interests. It also serves as a reliable source of factual reporting that can prevent misinformation. Moreover, it can influence national audiences as some local stories may have wider implications for politics, environment or crime. Hence, detecting the exact geolocation and impact scope of local news is crucial for news recommendation systems. There are two fundamental things required in this process, (1) classify whether an article belongs to local news, and (2) identify the geolocation of the article and its scope of influence to recommend it to appropriate users. In this paper, we focus on the second step and propose (1) an efficient approach to determine the location and radius of local news articles, (2) a method to reconcile the user's location with the article's location, and (3) a metric to evaluate the quality of the local news feed. We demonstrate that our technique is scalable and effective in serving hyperlocal news to users worldwide.