Personalizing Trust in Online Auctions

J O'Donovan, V Evrim, B Smyth, D McLeod, Patrick Nixon

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

    Abstract

    The amount of business taking place in online marketplaces such as eBay is growing rapidly. At the end of 2005 eBay Inc. reported annual growth rates of 42.5% [3] and in February 2006 received 3 million user feedback comments per day [1]. Now we are faced with the task of using the limited information provided on auction sites to transact with complete strangers with whom we will most likely only interact with once. People will naturally be comfortable with old fashioned "corner store" business practice [14], based on a person to person trust which is lacking in large-scale electronic marketplaces such as eBay and Amazon.com. We analyse reasons why the current feedback scores on eBay and most other online auctions are too positive. We introduce AuctionRules, a trust-mining algorithm which captures subtle indications of negativity from user comments in cases where users have rated a sale as positive but still voiced some grievance in their feedback. We explain how these new trust values can be propagated using a graph-representation of the eBay marketplace to provide personalized trust values for both parties in a potential transaction. Our experimental results show that AuctionRules beats seven benchmark algorithms by up to 21%, achieving up to 97.5% accuracy, with a false negative rate of 0% in comment classification tests compared with up to 8.5% from other algorithms tested.
    LanguageEnglish
    Title of host publicationUnknown Host Publication
    EditorsP Peppas and A Perini L Penserini
    PublisherIOS Press
    Pages72-83
    Number of pages12
    ISBN (Print)1586036459
    Publication statusPublished - 2006
    EventStairs 2006 : proceedings of the third starting AI researchers' symposium - Riva del Garda, Italy
    Duration: 1 Jan 2006 → …

    Conference

    ConferenceStairs 2006 : proceedings of the third starting AI researchers' symposium
    Period1/01/06 → …

    Fingerprint

    Feedback
    Electronic scales
    Industry
    Sales

    Keywords

    • n/a

    Cite this

    O'Donovan, J., Evrim, V., Smyth, B., McLeod, D., & Nixon, P. (2006). Personalizing Trust in Online Auctions. In P. P. A. A. P. L Penserini (Ed.), Unknown Host Publication (pp. 72-83). IOS Press.
    O'Donovan, J ; Evrim, V ; Smyth, B ; McLeod, D ; Nixon, Patrick. / Personalizing Trust in Online Auctions. Unknown Host Publication. editor / P Peppas and A Perini L Penserini. IOS Press, 2006. pp. 72-83
    @inproceedings{19fa4e4978f1428d8d640ccd0bd77f2c,
    title = "Personalizing Trust in Online Auctions",
    abstract = "The amount of business taking place in online marketplaces such as eBay is growing rapidly. At the end of 2005 eBay Inc. reported annual growth rates of 42.5{\%} [3] and in February 2006 received 3 million user feedback comments per day [1]. Now we are faced with the task of using the limited information provided on auction sites to transact with complete strangers with whom we will most likely only interact with once. People will naturally be comfortable with old fashioned {"}corner store{"} business practice [14], based on a person to person trust which is lacking in large-scale electronic marketplaces such as eBay and Amazon.com. We analyse reasons why the current feedback scores on eBay and most other online auctions are too positive. We introduce AuctionRules, a trust-mining algorithm which captures subtle indications of negativity from user comments in cases where users have rated a sale as positive but still voiced some grievance in their feedback. We explain how these new trust values can be propagated using a graph-representation of the eBay marketplace to provide personalized trust values for both parties in a potential transaction. Our experimental results show that AuctionRules beats seven benchmark algorithms by up to 21{\%}, achieving up to 97.5{\%} accuracy, with a false negative rate of 0{\%} in comment classification tests compared with up to 8.5{\%} from other algorithms tested.",
    keywords = "n/a",
    author = "J O'Donovan and V Evrim and B Smyth and D McLeod and Patrick Nixon",
    year = "2006",
    language = "English",
    isbn = "1586036459",
    pages = "72--83",
    editor = "{L Penserini}, {P Peppas and A Perini}",
    booktitle = "Unknown Host Publication",
    publisher = "IOS Press",
    address = "Netherlands",

    }

    O'Donovan, J, Evrim, V, Smyth, B, McLeod, D & Nixon, P 2006, Personalizing Trust in Online Auctions. in PPAAP L Penserini (ed.), Unknown Host Publication. IOS Press, pp. 72-83, Stairs 2006 : proceedings of the third starting AI researchers' symposium, 1/01/06.

    Personalizing Trust in Online Auctions. / O'Donovan, J; Evrim, V; Smyth, B; McLeod, D; Nixon, Patrick.

    Unknown Host Publication. ed. / P Peppas and A Perini L Penserini. IOS Press, 2006. p. 72-83.

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

    TY - GEN

    T1 - Personalizing Trust in Online Auctions

    AU - O'Donovan, J

    AU - Evrim, V

    AU - Smyth, B

    AU - McLeod, D

    AU - Nixon, Patrick

    PY - 2006

    Y1 - 2006

    N2 - The amount of business taking place in online marketplaces such as eBay is growing rapidly. At the end of 2005 eBay Inc. reported annual growth rates of 42.5% [3] and in February 2006 received 3 million user feedback comments per day [1]. Now we are faced with the task of using the limited information provided on auction sites to transact with complete strangers with whom we will most likely only interact with once. People will naturally be comfortable with old fashioned "corner store" business practice [14], based on a person to person trust which is lacking in large-scale electronic marketplaces such as eBay and Amazon.com. We analyse reasons why the current feedback scores on eBay and most other online auctions are too positive. We introduce AuctionRules, a trust-mining algorithm which captures subtle indications of negativity from user comments in cases where users have rated a sale as positive but still voiced some grievance in their feedback. We explain how these new trust values can be propagated using a graph-representation of the eBay marketplace to provide personalized trust values for both parties in a potential transaction. Our experimental results show that AuctionRules beats seven benchmark algorithms by up to 21%, achieving up to 97.5% accuracy, with a false negative rate of 0% in comment classification tests compared with up to 8.5% from other algorithms tested.

    AB - The amount of business taking place in online marketplaces such as eBay is growing rapidly. At the end of 2005 eBay Inc. reported annual growth rates of 42.5% [3] and in February 2006 received 3 million user feedback comments per day [1]. Now we are faced with the task of using the limited information provided on auction sites to transact with complete strangers with whom we will most likely only interact with once. People will naturally be comfortable with old fashioned "corner store" business practice [14], based on a person to person trust which is lacking in large-scale electronic marketplaces such as eBay and Amazon.com. We analyse reasons why the current feedback scores on eBay and most other online auctions are too positive. We introduce AuctionRules, a trust-mining algorithm which captures subtle indications of negativity from user comments in cases where users have rated a sale as positive but still voiced some grievance in their feedback. We explain how these new trust values can be propagated using a graph-representation of the eBay marketplace to provide personalized trust values for both parties in a potential transaction. Our experimental results show that AuctionRules beats seven benchmark algorithms by up to 21%, achieving up to 97.5% accuracy, with a false negative rate of 0% in comment classification tests compared with up to 8.5% from other algorithms tested.

    KW - n/a

    M3 - Conference contribution

    SN - 1586036459

    SP - 72

    EP - 83

    BT - Unknown Host Publication

    A2 - L Penserini, P Peppas and A Perini

    PB - IOS Press

    ER -

    O'Donovan J, Evrim V, Smyth B, McLeod D, Nixon P. Personalizing Trust in Online Auctions. In L Penserini PPAAP, editor, Unknown Host Publication. IOS Press. 2006. p. 72-83