Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Aspect extraction for sentiment analysis in Arabic dialect

Alawami, Alawya (2017) Aspect extraction for sentiment analysis in Arabic dialect. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

Download (1MB) | Preview


The increase of the user-generated content on the web led to the explosion of opinionated text which facilitated opinion mining research. Despite the popularity of this research field in English text and the large number of Arabic speakers who contribute continuously to the web content, Arabic opinion mining has not received much attention due to the lack of reliable NLP tools and an accepted/comprehensive dataset. While English opinion mining has been studied extensively, Arabic opinion mining hasn’t received as much attention. The work that exists in sentiment analysis is limited to news, blogs written in Modern Standard Arabic and few studies on social media and web reviews written in Arabic dialect. Moreover, most of the work done has been done at the document and sentence level and to best of our knowledge, there is no work on a more fine-grained level. In this work, we take a more fine-grained approach to Arabic opinion mining at the aspect level through experimentation with methods that have been used in English Aspect extraction. Further, we are also contributing a dataset that can be used for further research on Arabic dialect.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Alawami, Alawyaaaa93@pitt.eduaaa930000-0002-5611-8273
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairSpring, Mspring@pitt.eduSPRING
Committee MemberLin, Yu-Ruyurulin@pitt.eduYURULIN
Committee MemberHirtle, Stephen C.hirtle@pitt.eduHIRTLE
Committee MemberDiab,
Date: 21 September 2017
Date Type: Publication
Defense Date: 30 May 2017
Approval Date: 21 September 2017
Submission Date: 13 September 2017
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 107
Institution: University of Pittsburgh
Schools and Programs: School of Information Sciences > Information Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Arabic, NLP, Opinion mining, aspect extraction
Date Deposited: 21 Sep 2017 18:31
Last Modified: 21 Sep 2017 18:31


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item