Explicit and implicit user preferences in online dating

Authors:
Joshua Akehurst;Irena Koprinska;Kalina Yacef;Luiz Pizzato;Judy Kay;Tomasz Rej
Affiliations:
School of Information Technologies, University of Sydney, Australia;School of Information Technologies, University of Sydney, Australia;School of Information Technologies, University of Sydney, Australia;School of Information Technologies, University of Sydney, Australia;School of Information Technologies, University of Sydney, Australia;School of Information Technologies, University of Sydney, Australia
Venue:
PAKDD'11 Proceedings of the 15th international conference on New Frontiers in Applied Data Mining
Year:
2011

Citing 4
Cited 2

In-depth behavior understanding and use: The behavior informatics approach

Information Sciences: an International Journal
Relevance and ranking in online dating systems

Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval
People recommendation based on aggregated bidirectional intentions in social network site

PKAW'10 Proceedings of the 11th international conference on Knowledge management and acquisition for smart systems and services
CCR: a content-collaborative reciprocal recommender for online dating

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three

Impression management through communication in online dating

Proceedings of the companion publication of the 17th ACM conference on Computer supported cooperative work & social computing
Recommending people to people: the nature of reciprocal recommenders with a case study in online dating

User Modeling and User-Adapted Interaction

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we study user behavior in online dating, in particular the differences between the implicit and explicit user preferences. The explicit preferences are stated by the user while the implicit preferences are inferred based on the user behavior on the website. We first show that the explicit preferences are not a good predictor of the success of user interactions. We then propose to learn the implicit preferences from both successful and unsuccessful interactions using a probabilistic machine learning method and show that the learned implicit preferences are a very good predictor of the success of user interactions. We also propose an approach that uses the explicit and implicit preferences to rank the candidates in our recommender system. The results show that the implicit ranking method is significantly more accurate than the explicit and that for a small number of recommendations it is comparable to the performance of the best method that is not based on user preferences.