Converging human knowledge for opinion mining

  • Jiacheng Liu
  • , Feilong Tang*
  • , Long Chen
  • , Liang Qiao
  • , Yanqin Yang
  • , Wenchao Xu
  • *Corresponding author for this work

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

1 Scopus citations

Abstract

Opinion mining focuses on analyzing opinions in documents. Existing most algorithms for mining opinion either are machine-only, leaving plenty of confused puzzles due to lacking human background knowledge, or using opinion dictionary from domain experts. The latter is expensive and hard to scale. In this paper, we propose a novel approach RULING (conveRging hUman knowLedge opInion miNinG) for opinion mining, where human include both the crowd and the experts. Firstly, we propose a method for combining expert knowledge with the machine learning method. Then we use the prediction result to find out the hard item, and classify them using crowdsourcing. This method can scale better than the previous methods and get a better result. Experimental results demonstrate our RULING approach outperforms related proposals in terms of classification performance.

Original languageEnglish
Title of host publicationInnovative Mobile and Internet Services in Ubiquitous Computing - Proceedings of the 11th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, IMIS 2017
EditorsTomoya Enokido, Leonard Barolli
PublisherSpringer Verlag
Pages219-230
Number of pages12
ISBN (Print)9783319615417
DOIs
StatePublished - 2017
Externally publishedYes
Event11th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, IMIS 2017 - Torino, Italy
Duration: 10 Jul 201712 Jul 2017

Publication series

NameAdvances in Intelligent Systems and Computing
Volume612
ISSN (Print)2194-5357

Conference

Conference11th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, IMIS 2017
Country/TerritoryItaly
CityTorino
Period10/07/1712/07/17

Fingerprint

Dive into the research topics of 'Converging human knowledge for opinion mining'. Together they form a unique fingerprint.

Cite this