Real-Time Summarization of Twitter

TL;DR

This paper presents a real-time Twitter summarization system that classifies relevant tweets using Dirichlet scoring and aims to improve notification relevance and reduce redundancy.

Contribution

It introduces a Dirichlet score-based classification approach for real-time Twitter summarization and discusses algorithms for removing redundant tweets.

Findings

The approach achieves good performance on MAP, CG, and DCG metrics.

Dirichlet scoring effectively classifies relevant tweets.

Redundancy removal algorithms are proposed for improved notification quality.

Abstract

In this paper, we describe our approaches to TREC Real-Time Summarization of Twitter. We focus on real time push notification scenario, which requires a system monitors the stream of sampled tweets and returns the tweets relevant and novel to given interest profiles. Dirichlet score with and with very little smoothing (baseline) are employed to classify whether a tweet is relevant to a given interest profile. Using metrics including Mean Average Precision (MAP, cumulative gain (CG) and discount cumulative gain (DCG), the experiment indicates that our approach has a good performance. It is also desired to remove the redundant tweets from the pushing queue. Due to the precision limit, we only describe the algorithm in this paper.