Jiho Han Ronny Dowon Ko Objective automatically generate the summary of review extracting the strengthweakness of the product Use NLP techniques to predict ratings Similar to sentimental analysis ID: 812188
Download The PPT/PDF document "Automatic Product Profiling via NLP" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Automatic Product Profiling via NLP
Jiho
Han
Ronny (
Dowon
)
Ko
Slide2Objective:
automatically generate the summary of review extracting the strength/weakness of the product
Use NLP techniques to predict ratingsSimilar to sentimental analysisKey Insight: Imposing market structure assumptionDifferent type of information extractionAmazon review text
Automatic Product Profiling via NLP
Slide3Opinion = (orientation, polarity)
Overview
Review Texts
Orientation
Profile
Rating
∞
m
k
Slide4Predicting model
Slide5Steps
Slide6Parsing – through Stanford NLP syntax parser
Initializing orientation and polarity
Selecting polarity words through decision tree (Max-Ent)Orientation using N-gram (uni + bi)Use wordnet when testingExtract market profiling and pricing kernel
Update word polarity
Repeat until no more
improvement
Steps (cont’d)
Slide7Extract the words that have significant effect on rating (in terms of maximizing entropy)
Initializing Decision Tree
Slide8Initial word polarity
Resul
Slide9Change in polarity
Performance
Result (cont’d)