How to merge three different methods for information filtering ?

TL;DR

This paper explores merging three different methods for information filtering on Twitter to improve online reputation monitoring, demonstrating competitive performance and analyzing the impact of merging strategies.

Contribution

It introduces three approaches for filtering relevant tweets about entities and evaluates how merging strategies affect filtering performance.

Findings

Merging strategies can significantly impact filtering performance.

All three approaches are competitive with state-of-the-art methods.

Evaluation conducted within the RepLab-2013 Filtering task.

Abstract

Twitter is now a gold marketing tool for entities concerned with online reputation. To automatically monitor online reputation of entities , systems have to deal with ambiguous entity names, polarity detection and topic detection. We propose three approaches to tackle the first issue: monitoring Twitter in order to find relevant tweets about a given entity. Evaluated within the framework of the RepLab-2013 Filtering task, each of them has been shown competitive with state-of-the-art approaches. Mainly we investigate on how much merging strategies may impact performances on a filtering task according to the evaluation measure.