Exploiting emoticons in sentiment analysis

Alexander Hogenboom, Daniella Bal, Flavius Frasincar, Malissa Bal, Franciska M.G. de Jong, Uzay Kaymak

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    98 Citations (Scopus)
    2435 Downloads (Pure)

    Abstract

    As people increasingly use emoticons in text in order to ex- press, stress, or disambiguate their sentiment, it is crucial for automated sentiment analysis tools to correctly account for such graphical cues for sentiment. We analyze how emoti-cons typically convey sentiment and demonstrate how we can exploit this by using a novel, manually created emoticon sentiment lexicon in order to improve a state-of-the-art lexicon-based sentiment classication method. We evaluate our approach on 2,080 Dutch tweets and forum mes- sages, which all contain emoticons and have been manually annotated for sentiment. On this corpus, paragraph-level accounting for sentiment implied by emoticons signicantly improves sentiment classication accuracy. This indicates that whenever emoticons are used, their associated senti- ment dominates the sentiment conveyed by textual cues and forms a good proxy for intended sentiment.
    Original languageUndefined
    Title of host publicationProceedings of the 28th Annual ACM Symposium on Applied Computing, SAC 2013
    Place of PublicationNew York
    PublisherAssociation for Computing Machinery (ACM)
    Pages703-710
    Number of pages8
    ISBN (Print)978-1-4503-1656-9
    DOIs
    Publication statusPublished - Mar 2013
    Event28th Annual ACM Symposium on Applied Computing, SAC 2013 - Lisbon, Portugal
    Duration: 18 Mar 201322 Mar 2013
    Conference number: 28
    http://www.sigapp.org/sac/sac2013/

    Publication series

    Name
    PublisherACM

    Conference

    Conference28th Annual ACM Symposium on Applied Computing, SAC 2013
    Abbreviated titleSAC
    CountryPortugal
    CityLisbon
    Period18/03/1322/03/13
    Internet address

    Keywords

    • EWI-23268
    • METIS-296399
    • IR-85830

    Cite this

    Hogenboom, A., Bal, D., Frasincar, F., Bal, M., de Jong, F. M. G., & Kaymak, U. (2013). Exploiting emoticons in sentiment analysis. In Proceedings of the 28th Annual ACM Symposium on Applied Computing, SAC 2013 (pp. 703-710). New York: Association for Computing Machinery (ACM). https://doi.org/10.1145/2480362.2480498
    Hogenboom, Alexander ; Bal, Daniella ; Frasincar, Flavius ; Bal, Malissa ; de Jong, Franciska M.G. ; Kaymak, Uzay. / Exploiting emoticons in sentiment analysis. Proceedings of the 28th Annual ACM Symposium on Applied Computing, SAC 2013. New York : Association for Computing Machinery (ACM), 2013. pp. 703-710
    @inproceedings{1364313456bf42e58187a9bbad467cfc,
    title = "Exploiting emoticons in sentiment analysis",
    abstract = "As people increasingly use emoticons in text in order to ex- press, stress, or disambiguate their sentiment, it is crucial for automated sentiment analysis tools to correctly account for such graphical cues for sentiment. We analyze how emoti-cons typically convey sentiment and demonstrate how we can exploit this by using a novel, manually created emoticon sentiment lexicon in order to improve a state-of-the-art lexicon-based sentiment classication method. We evaluate our approach on 2,080 Dutch tweets and forum mes- sages, which all contain emoticons and have been manually annotated for sentiment. On this corpus, paragraph-level accounting for sentiment implied by emoticons signicantly improves sentiment classication accuracy. This indicates that whenever emoticons are used, their associated senti- ment dominates the sentiment conveyed by textual cues and forms a good proxy for intended sentiment.",
    keywords = "EWI-23268, METIS-296399, IR-85830",
    author = "Alexander Hogenboom and Daniella Bal and Flavius Frasincar and Malissa Bal and {de Jong}, {Franciska M.G.} and Uzay Kaymak",
    note = "10.1145/2480362.2480498",
    year = "2013",
    month = "3",
    doi = "10.1145/2480362.2480498",
    language = "Undefined",
    isbn = "978-1-4503-1656-9",
    publisher = "Association for Computing Machinery (ACM)",
    pages = "703--710",
    booktitle = "Proceedings of the 28th Annual ACM Symposium on Applied Computing, SAC 2013",
    address = "United States",

    }

    Hogenboom, A, Bal, D, Frasincar, F, Bal, M, de Jong, FMG & Kaymak, U 2013, Exploiting emoticons in sentiment analysis. in Proceedings of the 28th Annual ACM Symposium on Applied Computing, SAC 2013. Association for Computing Machinery (ACM), New York, pp. 703-710, 28th Annual ACM Symposium on Applied Computing, SAC 2013, Lisbon, Portugal, 18/03/13. https://doi.org/10.1145/2480362.2480498

    Exploiting emoticons in sentiment analysis. / Hogenboom, Alexander; Bal, Daniella; Frasincar, Flavius; Bal, Malissa; de Jong, Franciska M.G.; Kaymak, Uzay.

    Proceedings of the 28th Annual ACM Symposium on Applied Computing, SAC 2013. New York : Association for Computing Machinery (ACM), 2013. p. 703-710.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    TY - GEN

    T1 - Exploiting emoticons in sentiment analysis

    AU - Hogenboom, Alexander

    AU - Bal, Daniella

    AU - Frasincar, Flavius

    AU - Bal, Malissa

    AU - de Jong, Franciska M.G.

    AU - Kaymak, Uzay

    N1 - 10.1145/2480362.2480498

    PY - 2013/3

    Y1 - 2013/3

    N2 - As people increasingly use emoticons in text in order to ex- press, stress, or disambiguate their sentiment, it is crucial for automated sentiment analysis tools to correctly account for such graphical cues for sentiment. We analyze how emoti-cons typically convey sentiment and demonstrate how we can exploit this by using a novel, manually created emoticon sentiment lexicon in order to improve a state-of-the-art lexicon-based sentiment classication method. We evaluate our approach on 2,080 Dutch tweets and forum mes- sages, which all contain emoticons and have been manually annotated for sentiment. On this corpus, paragraph-level accounting for sentiment implied by emoticons signicantly improves sentiment classication accuracy. This indicates that whenever emoticons are used, their associated senti- ment dominates the sentiment conveyed by textual cues and forms a good proxy for intended sentiment.

    AB - As people increasingly use emoticons in text in order to ex- press, stress, or disambiguate their sentiment, it is crucial for automated sentiment analysis tools to correctly account for such graphical cues for sentiment. We analyze how emoti-cons typically convey sentiment and demonstrate how we can exploit this by using a novel, manually created emoticon sentiment lexicon in order to improve a state-of-the-art lexicon-based sentiment classication method. We evaluate our approach on 2,080 Dutch tweets and forum mes- sages, which all contain emoticons and have been manually annotated for sentiment. On this corpus, paragraph-level accounting for sentiment implied by emoticons signicantly improves sentiment classication accuracy. This indicates that whenever emoticons are used, their associated senti- ment dominates the sentiment conveyed by textual cues and forms a good proxy for intended sentiment.

    KW - EWI-23268

    KW - METIS-296399

    KW - IR-85830

    U2 - 10.1145/2480362.2480498

    DO - 10.1145/2480362.2480498

    M3 - Conference contribution

    SN - 978-1-4503-1656-9

    SP - 703

    EP - 710

    BT - Proceedings of the 28th Annual ACM Symposium on Applied Computing, SAC 2013

    PB - Association for Computing Machinery (ACM)

    CY - New York

    ER -

    Hogenboom A, Bal D, Frasincar F, Bal M, de Jong FMG, Kaymak U. Exploiting emoticons in sentiment analysis. In Proceedings of the 28th Annual ACM Symposium on Applied Computing, SAC 2013. New York: Association for Computing Machinery (ACM). 2013. p. 703-710 https://doi.org/10.1145/2480362.2480498