A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Customer sentiment appraisal from user-generated product reviews: a domain independent heuristic algorithm
Abstract Social media give new opportunities in customer survey and market survey for design inspiration with comments posted online by users spontaneously, in an oral-near language, and almost free of biases. Opinion mining techniques are being developed, especially customer sentiment analysis. These techniques are most of the time based on a text parsing and costly learning techniques based on target or domain-dependent corpora for getting a fine understanding of users’ preferences. On the contrary, in this paper, we propose an overall sentiment rating algorithm, accurate enough to deliver an overall rating on a product review, without a tedious customization to a product domain or customer polarities. The developed algorithm starts by a text parsing, uses a Dictionary of Affect Language to rate the word tree leaves and uses a series of basic heuristics to calculate backward an overall sentiment rating for the review. We validate it on the example of a commercial home theatre system, comparing our automated sentiment predictions with the one of a group of fifteen test subjects, resulting in a satisfactory correlation.
Customer sentiment appraisal from user-generated product reviews: a domain independent heuristic algorithm
Abstract Social media give new opportunities in customer survey and market survey for design inspiration with comments posted online by users spontaneously, in an oral-near language, and almost free of biases. Opinion mining techniques are being developed, especially customer sentiment analysis. These techniques are most of the time based on a text parsing and costly learning techniques based on target or domain-dependent corpora for getting a fine understanding of users’ preferences. On the contrary, in this paper, we propose an overall sentiment rating algorithm, accurate enough to deliver an overall rating on a product review, without a tedious customization to a product domain or customer polarities. The developed algorithm starts by a text parsing, uses a Dictionary of Affect Language to rate the word tree leaves and uses a series of basic heuristics to calculate backward an overall sentiment rating for the review. We validate it on the example of a commercial home theatre system, comparing our automated sentiment predictions with the one of a group of fifteen test subjects, resulting in a satisfactory correlation.
Customer sentiment appraisal from user-generated product reviews: a domain independent heuristic algorithm
Raghupathi, Dilip (author) / Yannou, Bernard (author) / Farel, Romain (author) / Poirson, Emilie (author)
2015-03-20
11 pages
Article (Journal)
Electronic Resource
English
User sentiment , Sentiment rating , Opinion mining , Design inspiration , Customer opinion , Product appraisal , Affective judgment Engineering , Engineering, general , Engineering Design , Mechanical Engineering , Computer-Aided Engineering (CAD, CAE) and Design , Electronics and Microelectronics, Instrumentation , Industrial Design
Significant Labels in Sentiment Analysis of Online Customer Reviews of Airlines
| DOAJ | 2020
Customer Feedback and Contractor Appraisal in Construction
| British Library Conference Proceedings | 1997
Predicting the Helpfulness of Online Customer Reviews across Different Product Types
| DOAJ | 2018
Customization oriented heuristic user interface design
| IEEE | 2006