Asymmetric recommendations

The interacting effects of social ratings' direction and strength on users' ratings

Oded Nov, Ofer Arazy

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    In social recommendation systems, users often publicly rate objects such as photos, news articles or consumer products. When they appear in aggregate, these ratings carry social signals such as the direction and strength of the raters' average opinion about the product. Using a controlled experiment we manipulated two central social signals-the direction and strength of social ratings of five popular consumer products-and examined their interacting effects on users' ratings. The results show an asymmetric user behavior, where the direction of perceived social rating has a negative effect on users' ratings if the direction of perceived social rating is negative, but no effect if the direction is positive. The strength of perceived social ratings did not have a significant effect on users' ratings. The findings highlight the potential for cascading adverse effects of small number of negative user ratings on subsequent users' opinions.

    Original languageEnglish (US)
    Title of host publicationRecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems
    PublisherAssociation for Computing Machinery, Inc
    Pages249-252
    Number of pages4
    ISBN (Print)9781450336925
    DOIs
    StatePublished - Sep 16 2015
    Event9th ACM Conference on Recommender Systems, RecSys 2015 - Vienna, Austria
    Duration: Sep 16 2015Sep 20 2015

    Other

    Other9th ACM Conference on Recommender Systems, RecSys 2015
    CountryAustria
    CityVienna
    Period9/16/159/20/15

    Fingerprint

    Consumer products
    Recommender systems
    Experiments

    Keywords

    • Anchoring
    • Recommender systems
    • Social influence
    • Social signals
    • Theory-driven design

    ASJC Scopus subject areas

    • Information Systems
    • Software
    • Computer Science Applications
    • Control and Systems Engineering

    Cite this

    Nov, O., & Arazy, O. (2015). Asymmetric recommendations: The interacting effects of social ratings' direction and strength on users' ratings. In RecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems (pp. 249-252). Association for Computing Machinery, Inc. https://doi.org/10.1145/2792838.2799667

    Asymmetric recommendations : The interacting effects of social ratings' direction and strength on users' ratings. / Nov, Oded; Arazy, Ofer.

    RecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2015. p. 249-252.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Nov, O & Arazy, O 2015, Asymmetric recommendations: The interacting effects of social ratings' direction and strength on users' ratings. in RecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, pp. 249-252, 9th ACM Conference on Recommender Systems, RecSys 2015, Vienna, Austria, 9/16/15. https://doi.org/10.1145/2792838.2799667
    Nov O, Arazy O. Asymmetric recommendations: The interacting effects of social ratings' direction and strength on users' ratings. In RecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc. 2015. p. 249-252 https://doi.org/10.1145/2792838.2799667
    Nov, Oded ; Arazy, Ofer. / Asymmetric recommendations : The interacting effects of social ratings' direction and strength on users' ratings. RecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2015. pp. 249-252
    @inproceedings{44ba27cd7cca4fefacc6daece916ec35,
    title = "Asymmetric recommendations: The interacting effects of social ratings' direction and strength on users' ratings",
    abstract = "In social recommendation systems, users often publicly rate objects such as photos, news articles or consumer products. When they appear in aggregate, these ratings carry social signals such as the direction and strength of the raters' average opinion about the product. Using a controlled experiment we manipulated two central social signals-the direction and strength of social ratings of five popular consumer products-and examined their interacting effects on users' ratings. The results show an asymmetric user behavior, where the direction of perceived social rating has a negative effect on users' ratings if the direction of perceived social rating is negative, but no effect if the direction is positive. The strength of perceived social ratings did not have a significant effect on users' ratings. The findings highlight the potential for cascading adverse effects of small number of negative user ratings on subsequent users' opinions.",
    keywords = "Anchoring, Recommender systems, Social influence, Social signals, Theory-driven design",
    author = "Oded Nov and Ofer Arazy",
    year = "2015",
    month = "9",
    day = "16",
    doi = "10.1145/2792838.2799667",
    language = "English (US)",
    isbn = "9781450336925",
    pages = "249--252",
    booktitle = "RecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems",
    publisher = "Association for Computing Machinery, Inc",

    }

    TY - GEN

    T1 - Asymmetric recommendations

    T2 - The interacting effects of social ratings' direction and strength on users' ratings

    AU - Nov, Oded

    AU - Arazy, Ofer

    PY - 2015/9/16

    Y1 - 2015/9/16

    N2 - In social recommendation systems, users often publicly rate objects such as photos, news articles or consumer products. When they appear in aggregate, these ratings carry social signals such as the direction and strength of the raters' average opinion about the product. Using a controlled experiment we manipulated two central social signals-the direction and strength of social ratings of five popular consumer products-and examined their interacting effects on users' ratings. The results show an asymmetric user behavior, where the direction of perceived social rating has a negative effect on users' ratings if the direction of perceived social rating is negative, but no effect if the direction is positive. The strength of perceived social ratings did not have a significant effect on users' ratings. The findings highlight the potential for cascading adverse effects of small number of negative user ratings on subsequent users' opinions.

    AB - In social recommendation systems, users often publicly rate objects such as photos, news articles or consumer products. When they appear in aggregate, these ratings carry social signals such as the direction and strength of the raters' average opinion about the product. Using a controlled experiment we manipulated two central social signals-the direction and strength of social ratings of five popular consumer products-and examined their interacting effects on users' ratings. The results show an asymmetric user behavior, where the direction of perceived social rating has a negative effect on users' ratings if the direction of perceived social rating is negative, but no effect if the direction is positive. The strength of perceived social ratings did not have a significant effect on users' ratings. The findings highlight the potential for cascading adverse effects of small number of negative user ratings on subsequent users' opinions.

    KW - Anchoring

    KW - Recommender systems

    KW - Social influence

    KW - Social signals

    KW - Theory-driven design

    UR - http://www.scopus.com/inward/record.url?scp=84962910952&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84962910952&partnerID=8YFLogxK

    U2 - 10.1145/2792838.2799667

    DO - 10.1145/2792838.2799667

    M3 - Conference contribution

    SN - 9781450336925

    SP - 249

    EP - 252

    BT - RecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems

    PB - Association for Computing Machinery, Inc

    ER -