Towards the extraction of customer-to-customer suggestions from reviews

    Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

    36 Citations (Scopus)

    Abstract

    State of the art in opinion mining mainly focuses on positive and negative sentiment summarisation of online customer reviews. We observe that reviewers tend to provide advice, recommendations and tips to the fellow customers on a variety of points of interest. In this work, we target the automatic detection of suggestion expressing sentences in customer reviews. This is a novel problem, and therefore to begin with, requires a well formed problem definition and benchmark dataset. This work provides a 3-fold contribution, namely, problem definition, benchmark dataset, and an approach for detection of suggestions for the customers. The problem is framed as a sentence classification problem, and a set of linguistically motivated features are proposed. Analysis of the nature of suggestions, and classification errors, highlight challenges and research opportunities associated with this problem.

    Original languageEnglish
    Title of host publicationConference Proceedings - EMNLP 2015
    Subtitle of host publicationConference on Empirical Methods in Natural Language Processing
    PublisherAssociation for Computational Linguistics (ACL)
    Pages2159-2167
    Number of pages9
    ISBN (Electronic)9781941643327
    DOIs
    Publication statusPublished - 2015
    EventConference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal
    Duration: 17 Sep 201521 Sep 2015

    Publication series

    NameConference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing

    Conference

    ConferenceConference on Empirical Methods in Natural Language Processing, EMNLP 2015
    Country/TerritoryPortugal
    CityLisbon
    Period17/09/1521/09/15

    Fingerprint

    Dive into the research topics of 'Towards the extraction of customer-to-customer suggestions from reviews'. Together they form a unique fingerprint.

    Cite this