Call of Papers for Current Volume ********************OnLine Paper Submission for Current Volume

Volume & Issue no: Volume 6, Issue 2, March - April 2017

____________________________________________________________________________________________________

Title:
Towards An Approach of Ontological Coreference Resolution for Sentiment Analysis
Author Name:
Le Thi Thuy, Vo Thanh Hung, Mai Duc Trung, Quan Thanh Tho, Phan Thi Tuoi
Abstract:
Abstract In this paper, we propose an ontology-based approach to tackle the problem of aspect-level sentiment analysis. This in an emerging trend in the field of NLP area nowadays, which aims at not only discovering the sentiments expressed by speakers, but also the objects (or aspects) targeted by those sentiment mentions. Ontology is considered highly useful to cope with this issue, due to its capability of capturing and representing concepts in a certain domain. However, ontology-based sentiment analysis suffers from the difficulty when handling anaphoric coreference of mentioned entities, which commonly occurs in textual documents. We address this problem by introducing an approach combining coreference resolution with ontology inference. First, we introduce Aspect-oriented Sentiment Ontology, capturing aspect-sentiment relationships via two specific relations of mentioned-by and implied-by. . Then, lightweight NLP techniques are combined with ontological knowledge base to support final sentiment rating decision. We have applied our approach on real datasets from Smartphone domain and promising initial results have been obtained. Keywords: aspect-level sentiment analysis; aspect-oriented sentiment ontology; coreference resolution; lightweight NLP
Cite this article:
Le Thi Thuy, Vo Thanh Hung, Mai Duc Trung, Quan Thanh Tho, Phan Thi Tuoi , " Towards An Approach of Ontological Coreference Resolution for Sentiment Analysis" , International Journal of Emerging Trends & Technology in Computer Science (IJETTCS) , Volume 6, Issue 2, March - April 2017 , pp. 102-112 , ISSN 2278-6856.
Full Text [PDF]                           Back to Current Issue

NOTE: Authors note that paper cannot be withdrawn at any condition once it is accepted. The Team of IJETTCS advise you, do not submit same article to the multiple journals simultaneously. This may create a problem for you. Please wait for review report which will take maximum 01 to 02 week. 

 

Contact us


International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)
ISSN 2278-6856
Frequency : 6 Issues/Year


E-mail: editor@ijettcs.org