Geographical diversification in POI recommendation: Toward improved coverage on interested areas

Jungkyu Han, Hayato Yamana

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

    5 Citations (Scopus)

    Abstract

    In recommending POIs(Point-Of-Interests), factors such as the diversity of the recommended POIs are as important as accuracy for providing a satisfactory recommendation. Although existing diversification methods can help POI recommender systems suggest more diverse POIs, they lack "geographical diversification," which results in the concentration of the supposedly "diverse" recommended POIs on "a small portion" in areas where the target-user is most active. This is caused by the neglect of POI locations in the diversification, i.e., existing diversification methods try to diversify the categories of recommended items. However, geographical diversification is essential for users whose activity interests comprise many sub-areas and who require a variety of recommended POIs encompassing all their activity interests. In this paper, we propose a novel proportional geographical diversification method that recommends a variety of POIs located in the activity district of a user such that the variety of sub-areas in the district is proportional to the frequency of his/her activity in each sub-area. We compare the performance of the proposed method with existing diversification methods using real datasets. The evaluation result shows that no method except the proposed one can significantly increase geographical diversity at the expense of tolerable accuracy loss.

    Original languageEnglish
    Title of host publicationRecSys 2017 - Proceedings of the 11th ACM Conference on Recommender Systems
    PublisherAssociation for Computing Machinery, Inc
    Pages224-228
    Number of pages5
    ISBN (Electronic)9781450346528
    DOIs
    Publication statusPublished - 2017 Aug 27
    Event11th ACM Conference on Recommender Systems, RecSys 2017 - Como, Italy
    Duration: 2017 Aug 272017 Aug 31

    Other

    Other11th ACM Conference on Recommender Systems, RecSys 2017
    CountryItaly
    CityComo
    Period17/8/2717/8/31

    Fingerprint

    Recommender systems

    Keywords

    • Diversity
    • Geographical diversity
    • POI recommendation

    ASJC Scopus subject areas

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

    Cite this

    Han, J., & Yamana, H. (2017). Geographical diversification in POI recommendation: Toward improved coverage on interested areas. In RecSys 2017 - Proceedings of the 11th ACM Conference on Recommender Systems (pp. 224-228). Association for Computing Machinery, Inc. https://doi.org/10.1145/3109859.3109884

    Geographical diversification in POI recommendation : Toward improved coverage on interested areas. / Han, Jungkyu; Yamana, Hayato.

    RecSys 2017 - Proceedings of the 11th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2017. p. 224-228.

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

    Han, J & Yamana, H 2017, Geographical diversification in POI recommendation: Toward improved coverage on interested areas. in RecSys 2017 - Proceedings of the 11th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, pp. 224-228, 11th ACM Conference on Recommender Systems, RecSys 2017, Como, Italy, 17/8/27. https://doi.org/10.1145/3109859.3109884
    Han J, Yamana H. Geographical diversification in POI recommendation: Toward improved coverage on interested areas. In RecSys 2017 - Proceedings of the 11th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc. 2017. p. 224-228 https://doi.org/10.1145/3109859.3109884
    Han, Jungkyu ; Yamana, Hayato. / Geographical diversification in POI recommendation : Toward improved coverage on interested areas. RecSys 2017 - Proceedings of the 11th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2017. pp. 224-228
    @inproceedings{f1abfbd63aa54c2cba3d26da4beae177,
    title = "Geographical diversification in POI recommendation: Toward improved coverage on interested areas",
    abstract = "In recommending POIs(Point-Of-Interests), factors such as the diversity of the recommended POIs are as important as accuracy for providing a satisfactory recommendation. Although existing diversification methods can help POI recommender systems suggest more diverse POIs, they lack {"}geographical diversification,{"} which results in the concentration of the supposedly {"}diverse{"} recommended POIs on {"}a small portion{"} in areas where the target-user is most active. This is caused by the neglect of POI locations in the diversification, i.e., existing diversification methods try to diversify the categories of recommended items. However, geographical diversification is essential for users whose activity interests comprise many sub-areas and who require a variety of recommended POIs encompassing all their activity interests. In this paper, we propose a novel proportional geographical diversification method that recommends a variety of POIs located in the activity district of a user such that the variety of sub-areas in the district is proportional to the frequency of his/her activity in each sub-area. We compare the performance of the proposed method with existing diversification methods using real datasets. The evaluation result shows that no method except the proposed one can significantly increase geographical diversity at the expense of tolerable accuracy loss.",
    keywords = "Diversity, Geographical diversity, POI recommendation",
    author = "Jungkyu Han and Hayato Yamana",
    year = "2017",
    month = "8",
    day = "27",
    doi = "10.1145/3109859.3109884",
    language = "English",
    pages = "224--228",
    booktitle = "RecSys 2017 - Proceedings of the 11th ACM Conference on Recommender Systems",
    publisher = "Association for Computing Machinery, Inc",

    }

    TY - GEN

    T1 - Geographical diversification in POI recommendation

    T2 - Toward improved coverage on interested areas

    AU - Han, Jungkyu

    AU - Yamana, Hayato

    PY - 2017/8/27

    Y1 - 2017/8/27

    N2 - In recommending POIs(Point-Of-Interests), factors such as the diversity of the recommended POIs are as important as accuracy for providing a satisfactory recommendation. Although existing diversification methods can help POI recommender systems suggest more diverse POIs, they lack "geographical diversification," which results in the concentration of the supposedly "diverse" recommended POIs on "a small portion" in areas where the target-user is most active. This is caused by the neglect of POI locations in the diversification, i.e., existing diversification methods try to diversify the categories of recommended items. However, geographical diversification is essential for users whose activity interests comprise many sub-areas and who require a variety of recommended POIs encompassing all their activity interests. In this paper, we propose a novel proportional geographical diversification method that recommends a variety of POIs located in the activity district of a user such that the variety of sub-areas in the district is proportional to the frequency of his/her activity in each sub-area. We compare the performance of the proposed method with existing diversification methods using real datasets. The evaluation result shows that no method except the proposed one can significantly increase geographical diversity at the expense of tolerable accuracy loss.

    AB - In recommending POIs(Point-Of-Interests), factors such as the diversity of the recommended POIs are as important as accuracy for providing a satisfactory recommendation. Although existing diversification methods can help POI recommender systems suggest more diverse POIs, they lack "geographical diversification," which results in the concentration of the supposedly "diverse" recommended POIs on "a small portion" in areas where the target-user is most active. This is caused by the neglect of POI locations in the diversification, i.e., existing diversification methods try to diversify the categories of recommended items. However, geographical diversification is essential for users whose activity interests comprise many sub-areas and who require a variety of recommended POIs encompassing all their activity interests. In this paper, we propose a novel proportional geographical diversification method that recommends a variety of POIs located in the activity district of a user such that the variety of sub-areas in the district is proportional to the frequency of his/her activity in each sub-area. We compare the performance of the proposed method with existing diversification methods using real datasets. The evaluation result shows that no method except the proposed one can significantly increase geographical diversity at the expense of tolerable accuracy loss.

    KW - Diversity

    KW - Geographical diversity

    KW - POI recommendation

    UR - http://www.scopus.com/inward/record.url?scp=85030453731&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85030453731&partnerID=8YFLogxK

    U2 - 10.1145/3109859.3109884

    DO - 10.1145/3109859.3109884

    M3 - Conference contribution

    AN - SCOPUS:85030453731

    SP - 224

    EP - 228

    BT - RecSys 2017 - Proceedings of the 11th ACM Conference on Recommender Systems

    PB - Association for Computing Machinery, Inc

    ER -