Characterization of User Online Dating Behavior and Preference on a Large Online Dating Site

Xia, Peng; Tu, Kun; Ribeiro, Bruno; Jiang, Hua; Wang, Xiaodong; Chen, Cindy X.; Liu, Benyuan; Towsley, Don

doi:10.1007/978-3-319-12188-8_9

Cited by 14 publications

(22 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yue Qian https://orcid.org/0000-0003-2120-5403 Note 1. For example, the median ages are 25 and 26 years, respectively, for male and female users of a major online dating site in China (Xia et al, 2014), whereas the median age in the general adult population is 41 years for both men and women over the age of 18 (authors' calculation based on Table 3-1 from the 2010 Census: www.stats.gov.cn/tjsj/pcsj/rkpc/ 6rp/indexch.htm). Similarly, 67% of female online daters and 53% of male online daters have at least a vocational college degree (Xia et al, 2014), but the respective figures in the general adult population are 12% for men and 10% for women (authors' calculation based on Table 4-1 from the 2010 Census).…”

Section: Declaration Of Conflicting Interestsmentioning

confidence: 99%

Mate selection among online daters in Shanghai: Why does education matter?

Xiao

Qian

2020

Chinese Journal of Sociology

View full text Add to dashboard Cite

Prior studies of assortative mating have shown that people tend to marry someone of the same educational level, but why individuals value a mate’s education and the process of mate selection itself remain a black box in predominantly quantitative studies. With online dating’s growing popularity, research needs to examine how online daters navigate dating markets given educational preferences they hold and ‘freedom of choice’ offered by technologies. This study aims to investigate individuals’ educational preferences and how educational preferences shape mate selection processes in online dating. In-depth interviews were conducted with 29 university-educated, heterosexual online daters (13 men, 16 women) in Shanghai. Data were analyzed through a combination of abductive and inductive coding strategies. Results showed that both educational levels and university prestige were primary mate selection criteria in online dating. Both genders considered educational sorting essential for achieving cultural matching, but only men emphasized the importance of spouse’s education for their future children’s education. Furthermore, guided by their educational preferences, online daters deliberately chose dating platforms and screened dating candidates. We argue that online daters’ emphasis on university prestige is rooted in China’s hierarchical higher education system, and gendered rationales for educational preferences stem from ingrained gender roles in Chinese families. Seemingly “personal” preferences are therefore shaped by cultural norms and institutional contexts. Moreover, results suggest that online dating may reinforce social closure among China’s educational elites.

show abstract

Section: Declaration Of Conflicting Interestsmentioning

confidence: 99%

Mate selection among online daters in Shanghai: Why does education matter?

Xiao

Qian

2020

Chinese Journal of Sociology

View full text Add to dashboard Cite

show abstract

“…Table 1 describes the characteristics of the dataset. More detailed description and analysis of the dataset can be found in our recent work [2,4]. For both males and females, we obtain the distribution of the number of messages sent by each user per week given that a user sends at least one message during the week, and plot its complementary cumulative density function (CCDF) in Figure 4(a).…”

Section: Dataset Overviewmentioning

confidence: 99%

Reciprocal Recommendation System for Online Dating

Xia

Liu

Sun

et al. 2015

Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2015

Self Cite

View full text Add to dashboard Cite

Online dating sites have become popular platforms for people to look for potential romantic partners. Different from traditional user-item recommendations where the goal is to match items (e.g., books, videos, etc) with a user's interests, a recommendation system for online dating aims to match people who are mutually interested in and likely to communicate with each other. We introduce similarity measures that capture the unique features and characteristics of the online dating network, for example, the interest similarity between two users if they send messages to same users, and attractiveness similarity if they receive messages from same users. A reciprocal score that measures the compatibility between a user and each potential dating candidate is computed and the recommendation list is generated to include users with top scores. The performance of our proposed recommendation system is evaluated on a realworld dataset from a major online dating site in China. The results show that our recommendation algorithms significantly outperform previously proposed approaches, and the collaborative filtering-based algorithms achieve much better performance than content-based algorithms in both precision and recall. Our results also reveal interesting behavioral difference between male and female users when it comes to looking for potential dates. In particular, males tend to be focused on their own interest and oblivious towards their attractiveness to potential dates, while females are more conscientious to their own attractiveness to the other side of the line.

show abstract

“…Table 1 describes the characteristics of the dataset. More detailed description and analysis of the dataset can be found in our recent work (Xia et al 2013(Xia et al , 2014b.…”

Section: Recommendation Algorithmsmentioning

confidence: 99%

“…In Xia et al (2014b), the authors analyze how user's sending and replying behavior correlate with several important user attributes, such as age, income, education level, and number of photos, and how much a user's actual preference deviates from his/her stated preference. The findings also correspond to the result of Pizzato et al (2010a) that the recommendation system built on user's implicit preference outperforms that built on user's explicit preference.…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, our dataset contains the communication traces between users, i.e., who sent or replied to messages to whom and the associated timestamps. As shown in our earlier paper (Xia et al 2014b), the communication trace of a user reflects his/her actual dating preference, which may significantly deviate from his/her stated preference and thus should play an important role in the design of the recommendation system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Design of reciprocal recommendation systems for online dating

Xia

Zhai

Liu

et al. 2016

Soc. Netw. Anal. Min.

Self Cite

View full text Add to dashboard Cite

Online dating sites have become popular platforms for people to look for potential romantic partners. Different from traditional user-item recommendations where the goal is to match items (e.g., books, videos) with a user's interests, a recommendation system for online dating aims to match people who are mutually interested in and likely to communicate with each other. We introduce similarity measures that capture the unique features and characteristics of the online dating network, for example, the interest similarity between two users if they send messages to same users, and attractiveness similarity if they receive messages from same users. A reciprocal score that measures the compatibility between a user and each potential dating candidate is computed, and the recommendation list is generated to include users with top scores. The performance of our proposed recommendation system is evaluated on a real-world dataset from a major online dating site in China. The results show that our recommendation algorithms significantly outperform previously proposed approaches, and the collaborative filtering-based algorithms achieve much better performance than contentbased algorithms in both precision and recall. Our results also reveal interesting behavioral difference between male and female users when it comes to looking for potential dates. In particular, males tend to be focused on their own interest and oblivious toward their attractiveness to potential dates, while females are more conscientious to their own attractiveness to the other side of the line.

show abstract

Characterization of User Online Dating Behavior and Preference on a Large Online Dating Site

Cited by 14 publications

References 16 publications

Mate selection among online daters in Shanghai: Why does education matter?

Mate selection among online daters in Shanghai: Why does education matter?

Reciprocal Recommendation System for Online Dating

Design of reciprocal recommendation systems for online dating

Contact Info

Product

Resources

About