ABSTRACT
Receiving poor results from a personalized recommendation system is frustrating. When users try to compensate by putting on a "different face" and game the system, the results can be even more frustrating. This paper investigates how to improve the user experience of such systems by: 1) adding personal photos to increase self-awareness, and 2) providing recommendations interspersed with personal questions. A 2x2 web experiment (N=56) within the context of an online dating match recommendation system was used to assess these two effects. Displaying a person's photo stabilized both response strategies and liking of a recommender's poor suggestions. Additionally, presenting all of the results together at the end was less frustrating than spreading them out. These results demonstrate that simple interface design decisions can have profound effects on user behaviors and attitudes with personalized recommendation systems.
Supplemental Material
Available for Download
Slides from the presentation
- Ellison, N., Heino, R. and Gibbs, J. (2006). Managing Impressions Online: Self-Presentation Processes in the Online Dating Environment. Journal of Computer-Mediated Communication, 11 (2).Google ScholarCross Ref
- Fejfar, M. C.&Hoyle, R. H. (2000). Effect of private self-awareness on negative affect and self-referent attribution: A quantitative review. Personality and Social Psychology Review. 4(2), 132--142.Google ScholarCross Ref
- Goffman, E. (1956). Presentation of Self in Everyday Life. Doubleday, New York.Google Scholar
- Hancock, J. T., Toma, C., and Ellison, N. (2007). The truth about lying in online dating profiles. CHI 2007. ACM, New York, NY. Google ScholarDigital Library
- Holbrook, A., Green, M., Krosnick, J. (2003). Telephone versus Face-to-Face Interviewing of National Probability Samples with Long Questionnaires: Comparisons of Respondent Satisficing and Social Desirability Response Bias. Public Opinion Quarterly 67:79--125.Google ScholarCross Ref
- Jones, Richard R., and Rorer, Leonard G. (1973). Response Biases and Trait Descriptive Adjectives. Multivariate Behavioral Research 8, 3, 313--330.Google ScholarCross Ref
- Paulhus, D.L. (1998). The Paulhus Deception Scales: BIDR Version 7. Toronto/Buffalo: Multi-Health Systems.Google Scholar
- Song, Hayeun. (2007). Seeing oneself in the media. ICA 2007.Google Scholar
- Zaslow, J. "If TiVo Thinks You Are Gay, Here's How To Set It Straight - Amazon.com Knows You, Too, Based on What You Buy; Why All the Cartoons?" The Wall Street Journal, sect. A, p. 1, November 26, 2002.Google Scholar
Index Terms
- My Dating Site Thinks I'm a Loser: effects of personal photos and presentation intervals on perceptions of recommender systems
Recommendations
Impression management through communication in online dating
CSCW Companion '14: Proceedings of the companion publication of the 17th ACM conference on Computer supported cooperative work & social computingPeople use online dating systems to form and create impressions of potential romantic partners. While there is a wealth of research on the use of profile pages for impression management in online dating systems, there is little work on how other forms ...
Reciprocal recommender system for online dating
RecSys '10: Proceedings of the fourth ACM conference on Recommender systemsReciprocal recommender is a class of recommender systems that is important for tasks where people are both the subject and the object of the recommendation; one such task is online dating. We have implemented RECON, a reciprocal recommender for online ...
HyRec: leveraging browsers for scalable recommenders
Middleware '14: Proceedings of the 15th International Middleware ConferenceThe ever-growing amount of data available on the Internet calls for personalization. Yet, the most effective personalization schemes, such as those based on collaborative filtering (CF), are notoriously resource greedy. This paper presents HyRec, an ...
Comments