Interest prediction via users’ actions on social media

Nozomi Nori, Danushka Bollegala, Mitsuru Ishizuka

    Research output: Contribution to journalArticle

    Abstract

    We propose a method to predict users’ interests by exploiting their various actions in social media. Actions performed by users in social media such as Twitter and Facebook have a fundamental property: user action involves multiple entities - e.g. sharing URLs with friends, bookmarking and tagging web pages, clicking a favorite button on a friend’s post etc. Consequently, it is appropriate to represent each user’s action at some point in time as a higher-order relation. We propose ActionGraph, a novel graph representation to model users’ higher-order actions. Each action performed by a user at some time point is represented by an action node. ActionGraph is a bipartite graph whose edges connect an action node to its involving entities, referred to as object nodes. Using real-world social media data, we empirically justify the proposed graph structure. We show that the prediction accuracy can be improved by adequately aggregating various actions. Moreover, our experimental results show that the proposed ActionGraph outperforms several baselines, including standard tensor analysis PARAFAC, a previously proposed state-of-the-art LDA-based method and other graph-based variants, in a user interest prediction task. Although a lot of research have been conducted to capture similarity between users or between users and resources by using graph, our paper indicates that an important factor for the prediction performance of the graph mining algorithm is the choice of the graph itself. In particular, our result indicates that in order to predict users activities, adding more specific information about users activities such as types of activities makes the graph mining algorithm more effective.

    Original languageEnglish
    Pages (from-to)613-625
    Number of pages13
    JournalTransactions of the Japanese Society for Artificial Intelligence
    Volume30
    Issue number4
    DOIs
    Publication statusPublished - 2015

    Fingerprint

    Websites
    Tensors

    Keywords

    • Collaborative filtering
    • Graph
    • Interest prediction
    • Social media
    • User modeling

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software

    Cite this

    Interest prediction via users’ actions on social media. / Nori, Nozomi; Bollegala, Danushka; Ishizuka, Mitsuru.

    In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 30, No. 4, 2015, p. 613-625.

    Research output: Contribution to journalArticle

    Nori, Nozomi ; Bollegala, Danushka ; Ishizuka, Mitsuru. / Interest prediction via users’ actions on social media. In: Transactions of the Japanese Society for Artificial Intelligence. 2015 ; Vol. 30, No. 4. pp. 613-625.
    @article{6ee663c38a814906b5a1610f88c5039a,
    title = "Interest prediction via users’ actions on social media",
    abstract = "We propose a method to predict users’ interests by exploiting their various actions in social media. Actions performed by users in social media such as Twitter and Facebook have a fundamental property: user action involves multiple entities - e.g. sharing URLs with friends, bookmarking and tagging web pages, clicking a favorite button on a friend’s post etc. Consequently, it is appropriate to represent each user’s action at some point in time as a higher-order relation. We propose ActionGraph, a novel graph representation to model users’ higher-order actions. Each action performed by a user at some time point is represented by an action node. ActionGraph is a bipartite graph whose edges connect an action node to its involving entities, referred to as object nodes. Using real-world social media data, we empirically justify the proposed graph structure. We show that the prediction accuracy can be improved by adequately aggregating various actions. Moreover, our experimental results show that the proposed ActionGraph outperforms several baselines, including standard tensor analysis PARAFAC, a previously proposed state-of-the-art LDA-based method and other graph-based variants, in a user interest prediction task. Although a lot of research have been conducted to capture similarity between users or between users and resources by using graph, our paper indicates that an important factor for the prediction performance of the graph mining algorithm is the choice of the graph itself. In particular, our result indicates that in order to predict users activities, adding more specific information about users activities such as types of activities makes the graph mining algorithm more effective.",
    keywords = "Collaborative filtering, Graph, Interest prediction, Social media, User modeling",
    author = "Nozomi Nori and Danushka Bollegala and Mitsuru Ishizuka",
    year = "2015",
    doi = "10.1527/tjsai.30_613",
    language = "English",
    volume = "30",
    pages = "613--625",
    journal = "Transactions of the Japanese Society for Artificial Intelligence",
    issn = "1346-0714",
    publisher = "Japanese Society for Artificial Intelligence",
    number = "4",

    }

    TY - JOUR

    T1 - Interest prediction via users’ actions on social media

    AU - Nori, Nozomi

    AU - Bollegala, Danushka

    AU - Ishizuka, Mitsuru

    PY - 2015

    Y1 - 2015

    N2 - We propose a method to predict users’ interests by exploiting their various actions in social media. Actions performed by users in social media such as Twitter and Facebook have a fundamental property: user action involves multiple entities - e.g. sharing URLs with friends, bookmarking and tagging web pages, clicking a favorite button on a friend’s post etc. Consequently, it is appropriate to represent each user’s action at some point in time as a higher-order relation. We propose ActionGraph, a novel graph representation to model users’ higher-order actions. Each action performed by a user at some time point is represented by an action node. ActionGraph is a bipartite graph whose edges connect an action node to its involving entities, referred to as object nodes. Using real-world social media data, we empirically justify the proposed graph structure. We show that the prediction accuracy can be improved by adequately aggregating various actions. Moreover, our experimental results show that the proposed ActionGraph outperforms several baselines, including standard tensor analysis PARAFAC, a previously proposed state-of-the-art LDA-based method and other graph-based variants, in a user interest prediction task. Although a lot of research have been conducted to capture similarity between users or between users and resources by using graph, our paper indicates that an important factor for the prediction performance of the graph mining algorithm is the choice of the graph itself. In particular, our result indicates that in order to predict users activities, adding more specific information about users activities such as types of activities makes the graph mining algorithm more effective.

    AB - We propose a method to predict users’ interests by exploiting their various actions in social media. Actions performed by users in social media such as Twitter and Facebook have a fundamental property: user action involves multiple entities - e.g. sharing URLs with friends, bookmarking and tagging web pages, clicking a favorite button on a friend’s post etc. Consequently, it is appropriate to represent each user’s action at some point in time as a higher-order relation. We propose ActionGraph, a novel graph representation to model users’ higher-order actions. Each action performed by a user at some time point is represented by an action node. ActionGraph is a bipartite graph whose edges connect an action node to its involving entities, referred to as object nodes. Using real-world social media data, we empirically justify the proposed graph structure. We show that the prediction accuracy can be improved by adequately aggregating various actions. Moreover, our experimental results show that the proposed ActionGraph outperforms several baselines, including standard tensor analysis PARAFAC, a previously proposed state-of-the-art LDA-based method and other graph-based variants, in a user interest prediction task. Although a lot of research have been conducted to capture similarity between users or between users and resources by using graph, our paper indicates that an important factor for the prediction performance of the graph mining algorithm is the choice of the graph itself. In particular, our result indicates that in order to predict users activities, adding more specific information about users activities such as types of activities makes the graph mining algorithm more effective.

    KW - Collaborative filtering

    KW - Graph

    KW - Interest prediction

    KW - Social media

    KW - User modeling

    UR - http://www.scopus.com/inward/record.url?scp=84936933980&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84936933980&partnerID=8YFLogxK

    U2 - 10.1527/tjsai.30_613

    DO - 10.1527/tjsai.30_613

    M3 - Article

    VL - 30

    SP - 613

    EP - 625

    JO - Transactions of the Japanese Society for Artificial Intelligence

    JF - Transactions of the Japanese Society for Artificial Intelligence

    SN - 1346-0714

    IS - 4

    ER -