TY - GEN
T1 - Feature based opinion mining for restaurant reviews
AU - Nithin, Y. R.
AU - Poornalatha, G.
N1 - Publisher Copyright:
© Springer International Publishing AG 2018.
PY - 2018
Y1 - 2018
N2 - Product reviews or customer feedback has become a platform for retailers to plan marketing strategy and also for new customers to select their appropriate product. Since the trend of e-commerce is increasing, an amount of customer reviews also has been increased to a greater extent. Consequently, it becomes a tough task for retailers as well as customers to read the reviews associated with the product. Sentiment analysis resolves this issue by scanning through free text reviews and providing the opinion summary. However, it does not provide detailed information, such as features on which the product is reviewed. Feature-based sentiment analysis methods increases the granularity of sentiment analysis by analyzing polarity associated with features in the given free text. The main objective of this work is to design a system that predicts polarity at aspect level and to design a score calculating scheme that defines the extent of polarity. Obtained feature - level scores are summarized according to users’ priority of interest.
AB - Product reviews or customer feedback has become a platform for retailers to plan marketing strategy and also for new customers to select their appropriate product. Since the trend of e-commerce is increasing, an amount of customer reviews also has been increased to a greater extent. Consequently, it becomes a tough task for retailers as well as customers to read the reviews associated with the product. Sentiment analysis resolves this issue by scanning through free text reviews and providing the opinion summary. However, it does not provide detailed information, such as features on which the product is reviewed. Feature-based sentiment analysis methods increases the granularity of sentiment analysis by analyzing polarity associated with features in the given free text. The main objective of this work is to design a system that predicts polarity at aspect level and to design a score calculating scheme that defines the extent of polarity. Obtained feature - level scores are summarized according to users’ priority of interest.
UR - https://www.scopus.com/pages/publications/85030157594
UR - https://www.scopus.com/inward/citedby.url?scp=85030157594&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-67934-1_27
DO - 10.1007/978-3-319-67934-1_27
M3 - Conference contribution
AN - SCOPUS:85030157594
SN - 9783319679334
VL - 678
T3 - Advances in Intelligent Systems and Computing
SP - 305
EP - 318
BT - Advances in Signal Processing and Intelligent Recognition Systems - Proceedings of 3rd International Symposium on Signal Processing and Intelligent Recognition Systems, SIRS-2017
A2 - Das, Swagatam
A2 - Krishnan, Sri
A2 - Corchado Rodriguez, Juan Manuel
A2 - Wozniak, Michal
A2 - Al-Jumeily, Dhiya
A2 - Thampi, Sabu M.
PB - Springer Verlag
T2 - 3rd International Symposium on Signal Processing and Intelligent Recognition Systems, SIRS 2017
Y2 - 13 September 2017 through 16 September 2017
ER -