Ranking rich mobile verticals based on clicks and abandonment

Mami Kawasaki, Inho Kang, Tetsuya Sakai

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

    Abstract

    We consider the problem of ranking rich verticals, which we call "cards," for a given mobile search query. Examples of card types in-clude "SHOP" (showing access and contact information of a shop), "WEATHER" (showing a weather forecast for a particular loca-tion), and "TV" (showing information about a TV programme). These cards can be highly visual and/or concise, and may often sat-isfy the user's information need without making her click on them. While this "good abandonment" of the search engine result page is ideal especially for mobile environments where the interaction be-tween the user and the search engine should be minimal, it poses a challenge for search engine companies whose ranking algorithms rely heavily on click data. In order to provide the right card types to the user for a given query, we propose a graph-based approach which extends a click-based automatic relevance estimation algo-rithm of Agrawal et al., by incorporating an abandonment-based preference rule. Using a real mobile query log from a commer-cial search engine, we constructed a data set containing 2,472 pair-wise card type preferences covering 992 distinct queries, by hiring three independent assessors. Our proposed method outperforms a click-only baseline by 53-68% in terms of card type preference accuracy. The improvement is also statistically highly significant, with p0:0000 according to the paired randomisation test.

    Original languageEnglish
    Title of host publicationCIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management
    PublisherAssociation for Computing Machinery
    Pages2127-2130
    Number of pages4
    VolumePart F131841
    ISBN (Electronic)9781450349185
    DOIs
    Publication statusPublished - 2017 Nov 6
    Event26th ACM International Conference on Information and Knowledge Management, CIKM 2017 - Singapore, Singapore
    Duration: 2017 Nov 62017 Nov 10

    Other

    Other26th ACM International Conference on Information and Knowledge Management, CIKM 2017
    CountrySingapore
    CitySingapore
    Period17/11/617/11/10

    Fingerprint

    Abandonment
    Ranking
    Search engine
    Query
    Weather
    Graph
    Interaction
    Randomization
    Information needs
    Hiring
    Query logs

    Keywords

    • Click data
    • Good abandonment
    • Mobile search
    • Vertical ranking

    ASJC Scopus subject areas

    • Business, Management and Accounting(all)
    • Decision Sciences(all)

    Cite this

    Kawasaki, M., Kang, I., & Sakai, T. (2017). Ranking rich mobile verticals based on clicks and abandonment. In CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management (Vol. Part F131841, pp. 2127-2130). Association for Computing Machinery. https://doi.org/10.1145/3132847.3133059

    Ranking rich mobile verticals based on clicks and abandonment. / Kawasaki, Mami; Kang, Inho; Sakai, Tetsuya.

    CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management. Vol. Part F131841 Association for Computing Machinery, 2017. p. 2127-2130.

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

    Kawasaki, M, Kang, I & Sakai, T 2017, Ranking rich mobile verticals based on clicks and abandonment. in CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management. vol. Part F131841, Association for Computing Machinery, pp. 2127-2130, 26th ACM International Conference on Information and Knowledge Management, CIKM 2017, Singapore, Singapore, 17/11/6. https://doi.org/10.1145/3132847.3133059
    Kawasaki M, Kang I, Sakai T. Ranking rich mobile verticals based on clicks and abandonment. In CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management. Vol. Part F131841. Association for Computing Machinery. 2017. p. 2127-2130 https://doi.org/10.1145/3132847.3133059
    Kawasaki, Mami ; Kang, Inho ; Sakai, Tetsuya. / Ranking rich mobile verticals based on clicks and abandonment. CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management. Vol. Part F131841 Association for Computing Machinery, 2017. pp. 2127-2130
    @inproceedings{8f6ab52525904fedb68a8a3565af79c3,
    title = "Ranking rich mobile verticals based on clicks and abandonment",
    abstract = "We consider the problem of ranking rich verticals, which we call {"}cards,{"} for a given mobile search query. Examples of card types in-clude {"}SHOP{"} (showing access and contact information of a shop), {"}WEATHER{"} (showing a weather forecast for a particular loca-tion), and {"}TV{"} (showing information about a TV programme). These cards can be highly visual and/or concise, and may often sat-isfy the user's information need without making her click on them. While this {"}good abandonment{"} of the search engine result page is ideal especially for mobile environments where the interaction be-tween the user and the search engine should be minimal, it poses a challenge for search engine companies whose ranking algorithms rely heavily on click data. In order to provide the right card types to the user for a given query, we propose a graph-based approach which extends a click-based automatic relevance estimation algo-rithm of Agrawal et al., by incorporating an abandonment-based preference rule. Using a real mobile query log from a commer-cial search engine, we constructed a data set containing 2,472 pair-wise card type preferences covering 992 distinct queries, by hiring three independent assessors. Our proposed method outperforms a click-only baseline by 53-68{\%} in terms of card type preference accuracy. The improvement is also statistically highly significant, with p0:0000 according to the paired randomisation test.",
    keywords = "Click data, Good abandonment, Mobile search, Vertical ranking",
    author = "Mami Kawasaki and Inho Kang and Tetsuya Sakai",
    year = "2017",
    month = "11",
    day = "6",
    doi = "10.1145/3132847.3133059",
    language = "English",
    volume = "Part F131841",
    pages = "2127--2130",
    booktitle = "CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management",
    publisher = "Association for Computing Machinery",

    }

    TY - GEN

    T1 - Ranking rich mobile verticals based on clicks and abandonment

    AU - Kawasaki, Mami

    AU - Kang, Inho

    AU - Sakai, Tetsuya

    PY - 2017/11/6

    Y1 - 2017/11/6

    N2 - We consider the problem of ranking rich verticals, which we call "cards," for a given mobile search query. Examples of card types in-clude "SHOP" (showing access and contact information of a shop), "WEATHER" (showing a weather forecast for a particular loca-tion), and "TV" (showing information about a TV programme). These cards can be highly visual and/or concise, and may often sat-isfy the user's information need without making her click on them. While this "good abandonment" of the search engine result page is ideal especially for mobile environments where the interaction be-tween the user and the search engine should be minimal, it poses a challenge for search engine companies whose ranking algorithms rely heavily on click data. In order to provide the right card types to the user for a given query, we propose a graph-based approach which extends a click-based automatic relevance estimation algo-rithm of Agrawal et al., by incorporating an abandonment-based preference rule. Using a real mobile query log from a commer-cial search engine, we constructed a data set containing 2,472 pair-wise card type preferences covering 992 distinct queries, by hiring three independent assessors. Our proposed method outperforms a click-only baseline by 53-68% in terms of card type preference accuracy. The improvement is also statistically highly significant, with p0:0000 according to the paired randomisation test.

    AB - We consider the problem of ranking rich verticals, which we call "cards," for a given mobile search query. Examples of card types in-clude "SHOP" (showing access and contact information of a shop), "WEATHER" (showing a weather forecast for a particular loca-tion), and "TV" (showing information about a TV programme). These cards can be highly visual and/or concise, and may often sat-isfy the user's information need without making her click on them. While this "good abandonment" of the search engine result page is ideal especially for mobile environments where the interaction be-tween the user and the search engine should be minimal, it poses a challenge for search engine companies whose ranking algorithms rely heavily on click data. In order to provide the right card types to the user for a given query, we propose a graph-based approach which extends a click-based automatic relevance estimation algo-rithm of Agrawal et al., by incorporating an abandonment-based preference rule. Using a real mobile query log from a commer-cial search engine, we constructed a data set containing 2,472 pair-wise card type preferences covering 992 distinct queries, by hiring three independent assessors. Our proposed method outperforms a click-only baseline by 53-68% in terms of card type preference accuracy. The improvement is also statistically highly significant, with p0:0000 according to the paired randomisation test.

    KW - Click data

    KW - Good abandonment

    KW - Mobile search

    KW - Vertical ranking

    UR - http://www.scopus.com/inward/record.url?scp=85037357022&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85037357022&partnerID=8YFLogxK

    U2 - 10.1145/3132847.3133059

    DO - 10.1145/3132847.3133059

    M3 - Conference contribution

    AN - SCOPUS:85037357022

    VL - Part F131841

    SP - 2127

    EP - 2130

    BT - CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management

    PB - Association for Computing Machinery

    ER -