Online markets are spreading quickly across the globe, supporting a huge network of product sales to billions of customers with various cultures, lifestyles, economic interests, and languages. These global markets introduce many novel opportunities -- as well as challenges. Our workshop, called XMRec, concerns the problem of recommending relevant products to users in a target market (e.g., a resource-scarce market) by leveraging data from similar high-resource markets, e.g. using data from the U.S. market to improve recommendations in a target market. We hypothesize that data from one market can be used to improve recommendation in another. We aim to create a dynamic and interactive atmosphere where researchers of diverse backgrounds and interests can discuss their ideas on cross-market recommendation and how it can be further pursued in the community. To this end, XMRec features a series of seed talks both from industry and academia, discussing the future of cross-market recommendation and its potentials as a new line of research. The seed talks will be followed by a panel discussion where a diverse set of researchers discuss their ideas and opinion about the topic. Finally, we will invite the participants and the panelists to take part in interactive brainstorming breakout sessions to further discuss their ideas. We aim to motivate a range of studies (like analyzing market-specific biases, conversational recommendation, and predicting early adopters) beyond the cross-domain recommendation by extending markets and content languages.
Time zone: Anywhere on Earth (AoE)
| CEST | EST | PST | China Time | Program |
|---|---|---|---|---|
| 15:00 - 15:10 | 09:00 - 09:10 | 06:00 - 06:10 | 21:00 - 21:10 | Openning |
| 15:10 - 15:55 | 09:10 - 09:55 | 06:10 - 06:55 | 21:10 - 21:55 | Keynote by Ben Carterette |
| 15:55 - 16:05 | 09:55 - 10:05 | 06:55 - 07:05 | 21:55 - 22:05 | Short break |
| 16:05 - 16:50 | 10:05 - 10:50 | 07:05 - 07:50 | 22:05 - 22:50 | Keynote by Julian McAuley |
| 16:50 - 17:15 | 10:50 - 11:15 | 07:50 - 08:15 | 22:50 - 23:15 | Long break and poster presentation of the accepted paper |
| 17:15 - 17:35 | 11:15 - 11:35 | 08:15 - 08:35 | 23:15 - 23:35 | Introduction to XMRec topics and panel discussion |
| 17:35 - 18:50 | 11:35 - 12:50 | 08:35 - 09:50 | 23:35 - 00:50 | Panel discussion |
| 18:50 - 19:00 | 12:50 - 13:00 | 09:50 - 10:00 | 00:50 - 01:00 | Closing |
XMRec participants should be registered at RecSys'21. However, we also need the list of registered participants to share the Zoom link of the workshop. Therefore, please register to XMRec, using Google Form.
Speaker: Ben Carterette, Spotify, USA
Abstract: Spotify is an international platform for music and podcast search and recommendation. Available in nearly 200 markets, it helps over 5 million creators connect to over 350 million listeners worldwide each month. But the ways in which people listen to, think about, and incorporate music and audio into their day-to-day lives can vary a great deal between cultures. What listeners in the U.S. want from an audio recommendation service may be very different from what listeners in India want, for example. In this talk, I will discuss some of the signals we see that indicate differences in listener behavior between markets; the extent to which "market" may (or may not) play a role in these differences; and given these differences how we can train recommendation models that connect listeners all over the world to the work of creators they'll love.
Speaker: Julian McAuley, UCSD, USA
Abstract: In this talk I'll give a high-level overview fair and unbiased machine learning, focusing on an emerging line of work that adapts fairness techniques to personalized recommendation, where questions of "fairness" generally center around underrepresented groups receiving reduced utility from recommendations. After giving a broad overview of the topic, I'll present our own work on marketing bias in recommender systems. Our work is related to the notion of self-congruity, i.e., users' tendency to select items whose marketing matches their self-image. We'll look at specific examples regarding gender identity and body type. Our main research questions are (1) to what extent is self-congruity reflected in actual purchase data; (2) do recommender systems have reduced utility to users whose identity is underrepresented among marketing images; and (3) can these negative effects be algorithmically mitigated?
Papers must be submitted by August 16, 2021 (23:59 AoE) via EasyChair. The submissions should be in English and prepared in PDF format according to the new single-column format (Microsoft Word or Latex formats). If you are using Overleaf, you can use the following code (\documentclass[manuscript]{acmart}). The review process is single-blind, handled electronically through EasyChair. Accepted papers will be included in the workshop proceedings and at least one author of each accepted contribution must attend the workshop. Accepted papers are given a poster presentation slot at the workshop. The ideal length of a paper for the XMRec workshop is between 4-8 pages (excluding references).
The following paper categories are welcome:
All accepted works will be presented at the workshop.
The workshop topics include but are not limited to:
For queries, please contact us via m.aliannejadi@uva.nl.