Maximizing recommender's influence in a social network

An information theoretic perspective

Basak Guler, Kaya Tutuncuoglu, Aylin Yener

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

    2 Citations (Scopus)

    Abstract

    We study a social network in which individuals make decisions influenced by a recommender as well as the previous actions taken by themselves or other users. The recommender aims to tailor its suggestions to maximize the benefit from utilizing social interactions. We refer to this benefit as the recommender's influence which, in essence, measures the value of controlling the specific suggestions offered to the individuals. We show that this influence can be quantified by the directed information between the suggestions and people's actions. Accordingly, we identify the precise relationship between the social network-based recommendation system and a finite state communication channel whose capacity analysis provides the solution for the influence maximization problem for the recommender. Our results demonstrate that a recommender that tailors its suggestions based on the social dynamics of its customer base can have a significantly greater influence.

    Original languageEnglish (US)
    Title of host publicationITW 2015 - 2015 IEEE Information Theory Workshop
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages262-266
    Number of pages5
    ISBN (Electronic)9781467378529
    DOIs
    StatePublished - Dec 17 2015
    EventIEEE Information Theory Workshop, ITW 2015 - Jeju Island, Korea, Republic of
    Duration: Oct 11 2015Oct 15 2015

    Other

    OtherIEEE Information Theory Workshop, ITW 2015
    CountryKorea, Republic of
    CityJeju Island
    Period10/11/1510/15/15

    Fingerprint

    Communication channels (information theory)
    Recommender systems
    Channel capacity

    All Science Journal Classification (ASJC) codes

    • Information Systems

    Cite this

    Guler, B., Tutuncuoglu, K., & Yener, A. (2015). Maximizing recommender's influence in a social network: An information theoretic perspective. In ITW 2015 - 2015 IEEE Information Theory Workshop (pp. 262-266). [7360776] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITWF.2015.7360776
    Guler, Basak ; Tutuncuoglu, Kaya ; Yener, Aylin. / Maximizing recommender's influence in a social network : An information theoretic perspective. ITW 2015 - 2015 IEEE Information Theory Workshop. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 262-266
    @inproceedings{232e781ed7064eb2ad26fd12ee1bc4fe,
    title = "Maximizing recommender's influence in a social network: An information theoretic perspective",
    abstract = "We study a social network in which individuals make decisions influenced by a recommender as well as the previous actions taken by themselves or other users. The recommender aims to tailor its suggestions to maximize the benefit from utilizing social interactions. We refer to this benefit as the recommender's influence which, in essence, measures the value of controlling the specific suggestions offered to the individuals. We show that this influence can be quantified by the directed information between the suggestions and people's actions. Accordingly, we identify the precise relationship between the social network-based recommendation system and a finite state communication channel whose capacity analysis provides the solution for the influence maximization problem for the recommender. Our results demonstrate that a recommender that tailors its suggestions based on the social dynamics of its customer base can have a significantly greater influence.",
    author = "Basak Guler and Kaya Tutuncuoglu and Aylin Yener",
    year = "2015",
    month = "12",
    day = "17",
    doi = "10.1109/ITWF.2015.7360776",
    language = "English (US)",
    pages = "262--266",
    booktitle = "ITW 2015 - 2015 IEEE Information Theory Workshop",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    Guler, B, Tutuncuoglu, K & Yener, A 2015, Maximizing recommender's influence in a social network: An information theoretic perspective. in ITW 2015 - 2015 IEEE Information Theory Workshop., 7360776, Institute of Electrical and Electronics Engineers Inc., pp. 262-266, IEEE Information Theory Workshop, ITW 2015, Jeju Island, Korea, Republic of, 10/11/15. https://doi.org/10.1109/ITWF.2015.7360776

    Maximizing recommender's influence in a social network : An information theoretic perspective. / Guler, Basak; Tutuncuoglu, Kaya; Yener, Aylin.

    ITW 2015 - 2015 IEEE Information Theory Workshop. Institute of Electrical and Electronics Engineers Inc., 2015. p. 262-266 7360776.

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

    TY - GEN

    T1 - Maximizing recommender's influence in a social network

    T2 - An information theoretic perspective

    AU - Guler, Basak

    AU - Tutuncuoglu, Kaya

    AU - Yener, Aylin

    PY - 2015/12/17

    Y1 - 2015/12/17

    N2 - We study a social network in which individuals make decisions influenced by a recommender as well as the previous actions taken by themselves or other users. The recommender aims to tailor its suggestions to maximize the benefit from utilizing social interactions. We refer to this benefit as the recommender's influence which, in essence, measures the value of controlling the specific suggestions offered to the individuals. We show that this influence can be quantified by the directed information between the suggestions and people's actions. Accordingly, we identify the precise relationship between the social network-based recommendation system and a finite state communication channel whose capacity analysis provides the solution for the influence maximization problem for the recommender. Our results demonstrate that a recommender that tailors its suggestions based on the social dynamics of its customer base can have a significantly greater influence.

    AB - We study a social network in which individuals make decisions influenced by a recommender as well as the previous actions taken by themselves or other users. The recommender aims to tailor its suggestions to maximize the benefit from utilizing social interactions. We refer to this benefit as the recommender's influence which, in essence, measures the value of controlling the specific suggestions offered to the individuals. We show that this influence can be quantified by the directed information between the suggestions and people's actions. Accordingly, we identify the precise relationship between the social network-based recommendation system and a finite state communication channel whose capacity analysis provides the solution for the influence maximization problem for the recommender. Our results demonstrate that a recommender that tailors its suggestions based on the social dynamics of its customer base can have a significantly greater influence.

    UR - http://www.scopus.com/inward/record.url?scp=84962701374&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84962701374&partnerID=8YFLogxK

    U2 - 10.1109/ITWF.2015.7360776

    DO - 10.1109/ITWF.2015.7360776

    M3 - Conference contribution

    SP - 262

    EP - 266

    BT - ITW 2015 - 2015 IEEE Information Theory Workshop

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -

    Guler B, Tutuncuoglu K, Yener A. Maximizing recommender's influence in a social network: An information theoretic perspective. In ITW 2015 - 2015 IEEE Information Theory Workshop. Institute of Electrical and Electronics Engineers Inc. 2015. p. 262-266. 7360776 https://doi.org/10.1109/ITWF.2015.7360776