AI

Abstract

In this paper, we consider the problem of discovering local events on the web, where events are entities extracted from pages with Schema.org annotations. Examples of such local events include small venue concerts, farmers markets, sports activities, etc. Given an event entity, we propose a graph-based framework for retrieving a ranked list of related events that a user is likely to be interested in or to attend. We demonstrate that this framework can be easily extended to the keyword search scenario as well, where the user issues a query to a search engine, hoping to find relevant events to attend. Due to the difficulty of obtaining ground-truth labels for event entities, which are temporal and are constrained by location, our general retrieval framework is unsupervised, and its graph-based formulation addresses (a) the challenge of feature sparseness and noisiness, and (b) semantic mismatch problem in a self-contained and principled manner.

To validate our methods, we collect human annotations and conduct a comprehensive empirical study, analyzing the performance of our methods with regard to relevance, recall, and diversity. This study shows that our graph-based framework is significantly better than any individual feature for both entity and keyword search scenarios, and can be further improved with minimal supervision. Finally, we demonstrate that our framework can be useful in understanding the temporal and the localized nature of the events on the web.