• Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage StatisticsView Google Analytics Statistics

    Rule based approach for aspect extraction from product reviews

    Thumbnail
    View/Open
    201611005 (251.6Kb)
    Date
    2018
    Author
    Rathore, Rahul
    Metadata
    Show full item record
    Abstract
    With the advent of technology, there has been an escalation in the usage of Internet and social media. This led to the generation of tremendous amounts of data on a daily basis. While sentiment analysis provides fantastic insights and has a wide range of real-world applications, the overall sentiment of a piece of text won't always pinpoint the root cause of an author's opinion. Aspect-Based Sentiment Analysis makes it easier to identify and determine the sentiment towards specific aspects in text. In our work, we have used Rule-Based method that extracts both implicit and explicit aspects from online product reviews using common-sense knowledge and sentence dependency trees, Convolutional Neural Network and Rule-Based method with Noun-Phrase Extractor, for aspect extraction from Laptop and Restaurants review datasets. Using the Rule-Based method with Noun- Phrase Extractor for aspect extraction, has shown a better performance in terms of Precision and Recall in both the datasets. Additionally, we also gained an insight into the cause of accumulation of noise on using noun phrase extractor and tried to address it by using the frequency based pruning technique.
    URI
    http://drsr.daiict.ac.in//handle/123456789/779
    Collections
    • M Tech Dissertations [923]

    Resource Centre copyright © 2006-2017 
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     


    Resource Centre copyright © 2006-2017 
    Contact Us | Send Feedback
    Theme by 
    Atmire NV