Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Real-Time Summarization of Twitter

Yixin Jin, Meiqi Wang, Meng Li, Wenjing Zhou, Yi Shen, Hao Liu

TL;DR

This work describes the approaches to TREC Real-Time Summarization of Twitter, which requires a system monitors the stream of sampled tweets and returns the tweets relevant and novel to given interest profiles.

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.

Real-Time Summarization of Twitter

TL;DR

This work describes the approaches to TREC Real-Time Summarization of Twitter, which requires a system monitors the stream of sampled tweets and returns the tweets relevant and novel to given interest profiles.

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.
Paper Structure (18 sections, 2 equations, 1 figure, 1 table, 1 algorithm)

This paper contains 18 sections, 2 equations, 1 figure, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Related Work
  4. Smoothing in Language Model
  5. Clustering
  6. Data and Preprocessing
  7. Methods
  8. Relevance
  9. Redundancy
  10. Experiment
  11. Setting
  12. Threshold $t$
  13. Results & Discussion
  14. Results
  15. Discussion
  16. ...and 3 more sections

Figures (1)

  • Figure 1: Precision and Recall of different thresholds for filtering system with and without smoothing. Top left panel: precision/recall versus threshold for baseline. Top right panel: recall versus precision for baseline. Bottom left panel: precision/recall versus threshold for filtering system with smoothing $\mu = 2500$. Bottom right panel: recall versus precision for filtering system with smoothing $\mu = 2500$.