Technical Papers Parallel session-V: Opinion mining approaches on Amazon product reviews: A comparative study
Abstract/Description
The process of extracting of people's opinion, experience and emotions from reviews, blogs and other sources is known as opinion mining. This paper compares our lexicon dictionary based approach with n-grams with three famous Machine Leaning (ML) algorithms, which are random forest learner with word vector, decision tree learner with document vector, and random forest with n-gram. To predict positive and negative sentiments, Amazon's Product Review dataset has been used. Accuracy of each of these algorithms is calculated by using ROC curve in order to compare which algorithm performs best on a given Amazon dataset. Experimental result shows that lexicon based approach outperforms other machine learning techniques.
Keywords
Sentiment analysis, Opinion mining, Lexicon approach, Machine learning, Product reviews, Semantic orientation
Location
Theatre 2, Aman Tower
Session Theme
Technical Papers Parallel session-V: Information Retrieval
Session Type
Parallel Technical Session
Session Chair
Dr. Khurram Junejo
Start Date
31-12-2017 2:40 PM
End Date
31-12-2017 3:00 PM
Recommended Citation
Ejaz, A., Turabee, Z., Rahim, M., & Khoja, S. (2017). Technical Papers Parallel session-V: Opinion mining approaches on Amazon product reviews: A comparative study. International Conference on Information and Communication Technologies. Retrieved from https://ir.iba.edu.pk/icict/2017/2017/30
COinS
Technical Papers Parallel session-V: Opinion mining approaches on Amazon product reviews: A comparative study
Theatre 2, Aman Tower
The process of extracting of people's opinion, experience and emotions from reviews, blogs and other sources is known as opinion mining. This paper compares our lexicon dictionary based approach with n-grams with three famous Machine Leaning (ML) algorithms, which are random forest learner with word vector, decision tree learner with document vector, and random forest with n-gram. To predict positive and negative sentiments, Amazon's Product Review dataset has been used. Accuracy of each of these algorithms is calculated by using ROC curve in order to compare which algorithm performs best on a given Amazon dataset. Experimental result shows that lexicon based approach outperforms other machine learning techniques.
