Streaming news sequential evolution model based on distributed representations

Zohaib Ahmad Khan, Qinglin Wang, Yu Liu, Yuan Li

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

In the field of advance scientific research where world is moving towards less human resources and more machine. Distributed representation has been one of the major field in which the prospects of neural usage have shifted immensely. In this research paper we have discussed how distributed representations are being used in streaming data clustering, and how to build a sequential evolution model for a streaming news website. Firstly, the stream news data collected from the web are cut to several slices chronologically; in addition, word2vec models are built in different time periods for every slice of data; lastly, compare the relationship of any target word in sequential word2vec models and analyze the evolutional procedure of the target word. An experimental result shows that our method is able to emerge the trend of the relationship between target words which can't be easily measured through traditional methods.

Original languageEnglish
Title of host publicationProceedings of the 36th Chinese Control Conference, CCC 2017
EditorsTao Liu, Qianchuan Zhao
PublisherIEEE Computer Society
Pages9647-9650
Number of pages4
ISBN (Electronic)9789881563934
DOIs
Publication statusPublished - 7 Sept 2017
Event36th Chinese Control Conference, CCC 2017 - Dalian, China
Duration: 26 Jul 201728 Jul 2017

Publication series

NameChinese Control Conference, CCC
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference36th Chinese Control Conference, CCC 2017
Country/TerritoryChina
CityDalian
Period26/07/1728/07/17

Keywords

  • Distributed Representation
  • Sequential Evolution Model
  • Streaming Text Analysis
  • Topic Trend

Fingerprint

Dive into the research topics of 'Streaming news sequential evolution model based on distributed representations'. Together they form a unique fingerprint.

Cite this