All over the world, future parents are facing the task of finding a suitable given name for their children. This choice is influenced by different factors, such as the social context, language, cultural background and especially personal taste. Although this task is omnipresent, little research has been conducted on the analysis and application of interrelations among given names from a data mining perspective.
We are pleased to organize this year’s ECML PKDD Discovery Challenge, tackling the task of recommending given names. The challenge comprises two phases: First, there will be an offline competition, where participants predict future search activities based on a training data set which is derived from the name search website nameling. Then, there will be an online competition, where participants integrate their recommender systems into the nameling website.
We are very much looking forward to this challenge and we expect many different contributions as we believe that the interplay of different influencing factors on the preference and choice of given names, links different disciplines and data mining approaches. The influence of personal taste, language and geographic user location, for example, presents an opportunity for context-aware recommendations. The influence of the social context of a user brings in the social network analysis community as another source to improve the quality of the recommender with its methods. Further, the etymological roots as well as connotations of names that have arisen over time (e.g., through popular cultural, political or religious bearers of a given name) suggest that methods based on inherent semantics and “content” may also yield successful recommendation approaches. Eventually, methods from the field of sentiment analysis may help to distinguish names which are popular because users like those names from those which are popular because users are interested in their context.
Workshop Format
The workshop is intended for one day. All participants are asked to prepare papers which will be presented either as oral presentations or posters. Submissions must be written in English, following the LNCS guidelines and must not exceed 12 pages including references and figures.
Papers must be submitted via EasyChair. The submissions to the workshop are elicited through an open call for papers and will undergo peer review by the program committee.
Important dates
Submission deadline: July 8th, 2013Notification of acceptance: July 15th, 2013Final paper submission: August, 23rd, 2013Workshop takes place on: July 27th, 2013
Program
| 10:45 – 11:15 | 20DC13 Opening |
| 11:15 – 11:35 | Marcos Aurélio Domingues, Ricardo Marcondes Marcacini, Solange Oliveira Rezende and Gustavo E. A. P. A. Batista: Improving the Recommendation of Given Names by Using Contextual Information |
| 11:35 – 11:55 | Dirk Schäfer and Robin Senge: Nameling Discovery Challenge – Collaborative Neighborhoods |
| 11:55 – 12:15 | Bernat Coma-Puig, Ernesto Diaz-Aviles and Wolfgang Nejdl: Collaborative Filtering Ensemble for Personalized Name Recommendation |
| 12:15 – 13:45 | Lunch break |
| 13:45 – 14:05 | Rafael Glauber, Angelo Loula and João Rocha-Junior: A Mixed Hybrid Recommender System for Given Names |
| 14:05 – 14:25 | Imannuel Bayer and Steffen Rendle: Factor Models for Recommending Given Names |
| 14:25 – 14:45 | Benjamin Letham: Similarity-Weighted Association Rules for a Name Recommender System |
| 14:45 – 15:15 | Discussion |
Proceedings
Authors of accepted papers will be invited to submit their paper for publication in the on-line proceedings which will appear in the CEUR-WS on-line proceedings series. At least one author of each accepted paper must attend the event in order to present the paper; accepted papers whose authors have not shown up at the workshop to present the paper will not be published in the proceedings.