Eliciting users' attitudes toward smart devices

Kai Zhan, Ingrid Zukerman, Masud Moshtaghi, Gwyneth Rees

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    Abstract

    This paper presents a study to determine users' attitudes toward smart devices. We conducted a web survey to elicit users' ratings for devices and combinations of tasks and devices; the results of this survey led to the development of a Recommender System (RS) for smart devices for particular tasks. We investigated user- and item-based Collaborative Filters, and compared their performance with that of global and demographic RS baselines. We then developed a technique based on Principal Components Analysis to select a subset of the original survey questions that supports the prediction of users' ratings for device-task combinations. Our results show that the accuracy of an RS that asks only a small subset of the survey questions is similar to that of an RS that predicts users' answers to one survey question on the basis of their answers to all the other questions.

    Original languageEnglish
    Title of host publicationProceedings of the 2016 Conference on User Modeling Adaptation and Personalization (UMAP 2016)
    Subtitle of host publicationJuly 13-17, 2016, Halifax, Nova Scotia, Canada
    EditorsLora Aroyo, Sidney D’Mello
    Place of PublicationNew York, New York
    PublisherAssociation for Computing Machinery (ACM)
    Pages175-184
    Number of pages10
    ISBN (Print)9781450343701
    DOIs
    Publication statusPublished - 13 Jul 2016
    EventInternational Conference on User Modelling, Adaptation, and Personalization (was AH and UM) 2016 - Halifax, Canada
    Duration: 13 Jul 201617 Jul 2016
    Conference number: 24th

    Conference

    ConferenceInternational Conference on User Modelling, Adaptation, and Personalization (was AH and UM) 2016
    Abbreviated titleUMAP 2016
    CountryCanada
    CityHalifax
    Period13/07/1617/07/16

    Keywords

    • Attitude modeling
    • Information elicitation
    • Rating prediction

    Cite this

    Zhan, K., Zukerman, I., Moshtaghi, M., & Rees, G. (2016). Eliciting users' attitudes toward smart devices. In L. Aroyo, & S. D’Mello (Eds.), Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization (UMAP 2016): July 13-17, 2016, Halifax, Nova Scotia, Canada (pp. 175-184). New York, New York: Association for Computing Machinery (ACM). https://doi.org/10.1145/2930238.2930241
    Zhan, Kai ; Zukerman, Ingrid ; Moshtaghi, Masud ; Rees, Gwyneth. / Eliciting users' attitudes toward smart devices. Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization (UMAP 2016): July 13-17, 2016, Halifax, Nova Scotia, Canada. editor / Lora Aroyo ; Sidney D’Mello. New York, New York : Association for Computing Machinery (ACM), 2016. pp. 175-184
    @inproceedings{886cc967c73e487d86c95e2bf8df23b2,
    title = "Eliciting users' attitudes toward smart devices",
    abstract = "This paper presents a study to determine users' attitudes toward smart devices. We conducted a web survey to elicit users' ratings for devices and combinations of tasks and devices; the results of this survey led to the development of a Recommender System (RS) for smart devices for particular tasks. We investigated user- and item-based Collaborative Filters, and compared their performance with that of global and demographic RS baselines. We then developed a technique based on Principal Components Analysis to select a subset of the original survey questions that supports the prediction of users' ratings for device-task combinations. Our results show that the accuracy of an RS that asks only a small subset of the survey questions is similar to that of an RS that predicts users' answers to one survey question on the basis of their answers to all the other questions.",
    keywords = "Attitude modeling, Information elicitation, Rating prediction",
    author = "Kai Zhan and Ingrid Zukerman and Masud Moshtaghi and Gwyneth Rees",
    year = "2016",
    month = "7",
    day = "13",
    doi = "10.1145/2930238.2930241",
    language = "English",
    isbn = "9781450343701",
    pages = "175--184",
    editor = "Lora Aroyo and Sidney D’Mello",
    booktitle = "Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization (UMAP 2016)",
    publisher = "Association for Computing Machinery (ACM)",
    address = "United States of America",

    }

    Zhan, K, Zukerman, I, Moshtaghi, M & Rees, G 2016, Eliciting users' attitudes toward smart devices. in L Aroyo & S D’Mello (eds), Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization (UMAP 2016): July 13-17, 2016, Halifax, Nova Scotia, Canada. Association for Computing Machinery (ACM), New York, New York, pp. 175-184, International Conference on User Modelling, Adaptation, and Personalization (was AH and UM) 2016, Halifax, Canada, 13/07/16. https://doi.org/10.1145/2930238.2930241

    Eliciting users' attitudes toward smart devices. / Zhan, Kai; Zukerman, Ingrid; Moshtaghi, Masud; Rees, Gwyneth.

    Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization (UMAP 2016): July 13-17, 2016, Halifax, Nova Scotia, Canada. ed. / Lora Aroyo; Sidney D’Mello. New York, New York : Association for Computing Machinery (ACM), 2016. p. 175-184.

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    TY - GEN

    T1 - Eliciting users' attitudes toward smart devices

    AU - Zhan, Kai

    AU - Zukerman, Ingrid

    AU - Moshtaghi, Masud

    AU - Rees, Gwyneth

    PY - 2016/7/13

    Y1 - 2016/7/13

    N2 - This paper presents a study to determine users' attitudes toward smart devices. We conducted a web survey to elicit users' ratings for devices and combinations of tasks and devices; the results of this survey led to the development of a Recommender System (RS) for smart devices for particular tasks. We investigated user- and item-based Collaborative Filters, and compared their performance with that of global and demographic RS baselines. We then developed a technique based on Principal Components Analysis to select a subset of the original survey questions that supports the prediction of users' ratings for device-task combinations. Our results show that the accuracy of an RS that asks only a small subset of the survey questions is similar to that of an RS that predicts users' answers to one survey question on the basis of their answers to all the other questions.

    AB - This paper presents a study to determine users' attitudes toward smart devices. We conducted a web survey to elicit users' ratings for devices and combinations of tasks and devices; the results of this survey led to the development of a Recommender System (RS) for smart devices for particular tasks. We investigated user- and item-based Collaborative Filters, and compared their performance with that of global and demographic RS baselines. We then developed a technique based on Principal Components Analysis to select a subset of the original survey questions that supports the prediction of users' ratings for device-task combinations. Our results show that the accuracy of an RS that asks only a small subset of the survey questions is similar to that of an RS that predicts users' answers to one survey question on the basis of their answers to all the other questions.

    KW - Attitude modeling

    KW - Information elicitation

    KW - Rating prediction

    UR - http://www.scopus.com/inward/record.url?scp=84984926997&partnerID=8YFLogxK

    U2 - 10.1145/2930238.2930241

    DO - 10.1145/2930238.2930241

    M3 - Conference Paper

    SN - 9781450343701

    SP - 175

    EP - 184

    BT - Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization (UMAP 2016)

    A2 - Aroyo, Lora

    A2 - D’Mello, Sidney

    PB - Association for Computing Machinery (ACM)

    CY - New York, New York

    ER -

    Zhan K, Zukerman I, Moshtaghi M, Rees G. Eliciting users' attitudes toward smart devices. In Aroyo L, D’Mello S, editors, Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization (UMAP 2016): July 13-17, 2016, Halifax, Nova Scotia, Canada. New York, New York: Association for Computing Machinery (ACM). 2016. p. 175-184 https://doi.org/10.1145/2930238.2930241