The 2021 SIGIR Workshop On eCommerce

July 15

    Previous editions: SIGIReCom'20 | SIGIReCom'19 | SIGIReCom'18 | SIGIReCom'17

    SIGIR Forum Article - Challenges and Research Opportunities in eCommerce Search and Recommendations

    *** Underline link for the workshop *** - Participate! [Workshop starts July 15 at 8.55 am EDT/ 2.55 pm CET]

    Accepted Papers


The SIGIR Workshop on eCommerce will serve as a platform for publication and discussion of Information Retrieval and NLP research & their applications in the domain of eCommerce. This workshop will bring together practitioners and researchers from academia and industry to discuss the challenges and approaches to product search and recommendation in eCommerce.

The theme of this year's workshop is fairness in search and recommendation for eCommerce.

SIGIR eCom is a full day workshop taking place on Thursday, July 15, 2021 in conjunction with SIGIR 2021. SIGIR eCom'21 will be a virtual workshop.

SIGIR eCom'21 Workshop Schedule

July 15, 2021 All times below in EDT - GMT-4
8:55 am EDT
5:55 am PDT
2:55 pm CET
Workshop Opening

9:00 am EDT
6:00 am PDT
3:00 pm CET
Contributed Papers Spotlight Session

A Deep Reinforcement Learning-Based Approach to Query-Free Interactive Target Item Retrieval
Anna Sepliarskaia, Sahika Genc and Maarten de Rijke

Preventing Contrast Effect Exploitation in Recommendations
Chris Nota, Georgios Theocharous, Michele Saad and Philip S. Thomas

Conditional Sequential Slate Optimization
Yipeng Zhang, Mingjian Lu, Saratchandra Indrakanti, Manojkumar Rangasamy Kannadasan and Abraham Bagherjeiran

10:00 am EDT Coffee Break
10:30 am EDT
07:30 am PDT
04:30 pm CET
Invited Talk
Why Bias Affects Machine Learning and What Can We Do About It?
Kushal Kafle    Adobe, USA
11:05 am EDT
08:05 am PDT
05:05 pm CET
Fashion AI and Algorithmic size advice
Julia Lasserre     Zalando, Europe
12:00 pm EDT
09:00 am PDT
06:00 pm CET
Long Break and Paper Discussion Session
12:45 pm EDT
09:45 am PDT
06:45 pm CET
Fact Checking Using Stance Detection and User Comments
Emine Yilmaz    UCL and Amazon, UK
1:40 pm EDT
10:40 am PDT
7:40 pm CET
Panel Discussion
Fairness in Search and Recommendation for eCommerce
Vanessa Murdock     Amazon, USA
Henriette Cramer     Spotify, USA
Michael Ekstrand     Boise State University, USA
Nadia Fawaz     Pinterest, USA
Alexandra Olteanu     Microsoft Research, Canada
3:00 pm EDT Coffee Break
3:30 pm EDT
12:30 pm PDT
9:30 pm CET
Invited Talk

Alex Beutel    Google, USA
4:05 - 5:30 pm EDT
1:05 - 2:30 pm PDT
10:05-11.30pm CET
Data Challenge Discussion and Overview and Best paper

Jacopo Tagliabue    Coveo, USA
5:30 pm EDT Group Discussion and Closing

Keynote Speakers

Emine Yilmaz, Amazon, UCL (UK)

Fact Checking Using Stance Detection and User Comments
Abstract:Misinformation regarding products could be a major problem that could have a significant effect on the trust and satisfaction of the users of e-commerce sites. Such misinformation could be present in two major forms: 1) Claims made about a product in product descriptions, and 2) Reviews posted about a product. In this talk, I will be talking about the methods we have developed for automatic detection of misinformation. I will first focus on the problem of stance detection, where the task is to categorize an overall position of a resource towards a claim into different classes such as agree, disagree, unrelated, etc. One of the major problems faced by current machine learning models used for stance detection is caused by a severe class imbalance among these classes. Hence, most models fail to correctly classify instances that fall into minority classes. In the first part of this talk, I will present a model that addresses this problem by proposing a hierarchical representation of these classes and show how such a model could achieve significant performance improvement especially in the classification of minority classes. In addition to stance detection, people’s comments or reviews are also quite informative regarding the truthfulness of the claim made. In the second part of this talk, I will present a model that uses information from people's replies to a claim that can be used to predict the truthfulness of the claims made, together with its uncertainty.

Speaker Bio

Emine Yilmaz is a Professor and Turing Fellow at University College London (UCL), Department of Computer Science, as well as an Amazon Scholar at Amazon Alexa Shopping. Between 2012 and 2019, she also worked as a research consultant for Microsoft Research Cambridge, where she used to work as a full-time researcher prior to joining UCL. Her research until now has received several awards including a Bloomberg Data Science Research Award in 2018, the Karen Sparck Jones Award in 2015 and the Google Faculty Research Award in 2014. Emine's current research interests include automatic misinformation detection, fairness and bias in machine learning algorithms and conversational assistants. She has published research papers extensively at major venues such as ACM SIGIR, CIKM and WSDM, gave several tutorials as part of top conferences, and organised various workshops. She has served in various roles such as the Best Paper Awards Chair for SIGIR 2021, Panels Chair for The Web Conf 2021, PC Chair for ECIR 2019, and PC Chair for ACM SIGIR 2018.

Julia Lasserre, Zalando (Germany)

Fashion AI and Algorithmic size advice
Abstract: Fashion is an enormous industry and offers incredible challenges. As a result it is rapidly developing as an interest for the scientific community, particularly in the field of computer vision. Fashion is intimate, it touches our personality and our body, and it can't be avoided :) In the first part of the talk, we will discuss Fashion AI and what challenges lie ahead of us at Zalando. In the second part, we will talk about our algorithmic size advice: what data we use and what kind of products we build to support our customers in buying the right size. If time allows, we will have a deep-dive into one algorithm.

Speaker Bio

Julia Lasserre has always been interested in the possibilities offered by machine learning and in applying various techniques to real-world problems. After receiving her PhD in machine learning and computer vision from Cambridge Uiversity, she did a post-doc in bioinformatics at the Max-Planck-Institute for Molecular Genetics, and then joined the industry. At Zalando, she has worked on different topics ranging from brand understanding to product tagging, active learning, representation learning and recommendations. She is currently an Principal Applied Scientist for the Size & Fit team and focuses on personalized size recommendations.

Invited Speakers

Kushal Kafle, Adobe (USA)

Why Bias Affects Machine Learning and What Can We Do About It?
Abstract:Learn about how our decisions regarding data, models, and evaluation play a role in perpetuating bias in machine learning systems, and how we can work towards mitigating their effects through smarter algorithmic and data choices. We look at examples from various computer vision and natural language processing tasks to understand how bias can enter the final deployed system. Recent advances in bias mitigation research have uncovered several techniques and algorithmic choices that can lessen the impacts of bias in ML systems. We look at a few classes of such techniques and examine their efficacy and best use case under different commonly encountered scenarios. Finally, we highlight the need to re-think how we analyze and evaluate the goodness of our models to avoid a false sense of progress.

Speaker Bio

Kushal Kafle is a research scientist in the vision group at Adobe Research. Kushal joined Adobe Research in March 2020, after completing his PhD at the Rochester Institute of Technology. In the past, he has completed research internships at Microsoft and Adobe Research. His work at Adobe Research currently focused on accurate and bias-free prediction and understanding of object attributes and their relationships in images. His broader research interests and expertise lie at the intersection of computer vision and natural language processing, with a specific focus on visual question answering (VQA), where he has published extensively. As an active member of the computer vision and NLP research community, he has served on the program committee of numerous conferences and Journals. He co-organized the annual international workshop on “Shortcomings in vision and language (SiVL)” held at ECCV 2018 and NAACL 2019 and is currently serving as guest associate editor for a special issue in the Frontiers Journal.

Alex Beutel, Google (USA)

Building and Understanding Recommenders for Long-Term User Experiences

Alex Beutel is a Senior Staff Research Scientist and team lead in Google Research, driving research spanning recommender systems, fairness, robustness, reinforcement learning, and ML for databases. He received his Ph.D. in 2016 from Carnegie Mellon University’s Computer Science Department, and previously received his B.S. from Duke University in computer science and physics. His Ph.D. thesis on large-scale user behavior modeling, covering recommender systems, fraud detection, and scalable machine learning, was given the SIGKDD 2017 Doctoral Dissertation Award Runner-Up. He received the Best Paper Award at KDD 2016 and ACM GIS 2010, was a finalist for best paper in KDD 2014, and was awarded the Facebook Fellowship in 2013 and the NSF Graduate Research Fellowship in 2011. More details can be found at

Panel Discussion

Topic: Fairness in Search and Recommendation for eCommerce
Vanessa Murdock

Henriette Cramer
Michael Ekstrand
Boise State University
Nadia Fawaz
Alexandra Olteanu
Microsoft Research

Call For Papers

We invite quality research contributions, position and opinion papers addressing relevant challenges in the domain of eCommerce. We invite submission of papers and posters representing original research, preliminary research results, proposals for new work, position and opinion papers. All submitted papers and posters will be single-blind and will be peer reviewed by an international program committee of researchers of high repute. Accepted submissions will be presented at the workshop.


         Topics of interest include, but are not limited to:

  • Ranking and Whole Page Relevance
  • -    Diversity in product search and recommendations
    -    Relevance models for multi-faceted entities
    -    The balance between business requirements and customer requirements (revenue vs. relevance)
    -    Ranking features and learning mechanisms (textual, image, structured data, customer behavior, reviews, ratings, social signals, etc.)
    -    Deterministic sorts (e.g. price low to high)
    -    Temporal dynamics and seasonality
  • Query Understanding
  • -    Query intent, query suggestions, and auto-completion
    -    Strategies for resolving low or zero recall queries
    -    Converting across modalities (e.g. text, structured data, images)
  • Document Understanding
  • -    Categorization and facets
    -    Reviews and sentiment analysis
  • Recommendation and Personalization
  • -    Personalization & contextualization, including the use of personal facets such as age, gender, location
    -    Blending recommendations and search results
  • Representations and Data
  • -    Semantic representation of products, queries, and customers
    -    Construction and use of knowledge graphs for eCommerce
  • IR Fundamentals for eCommerce
  • -    Cross-lingual search and machine translation
    -    Machine learning techniques for eCommerce applications
    -    Indexing and search in rapidly changing environments (e.g. auction sites)
    -    Experimentation techniques including AB testing and Multi-armed bandits
  • Other Topics
  • -    Trust and fairness in eCommerce 
    -    UX for eCommerce
    -    The role of search in trust and security for marketplaces
    -    Question answering and chat bots for eCommerce

Data/ Resource Track

In order to promote academic research in the eCommerce domain, we plan to accept a small number of high quality dataset contributions. These submissions should be accompanied by a clear and detailed description of the dataset, some potential questions and applications that arise from it. Preliminary empirical investigations conveying any insight about the data will increase the quality of the submission.

Submission Instructions

All papers will be peer reviewed (single-blind) by the program committee and judged by their relevance to the workshop, especially to the main themes identified above, and their potential to generate discussion. All submissions must be formatted according to the latest ACM SIG proceedings template available at (LaTeX users use sample-sigconf.tex as a template).

Submissions must describe work that is not previously published, not accepted for publication elsewhere, and not currently under review elsewhere. All submissions must be in English. The workshop follows a single-blind reviewing process. We do not accept anonymized submissions. Please note that at least one of the authors of each accepted paper must register for the workshop and present the paper.

Long paper limit: 8 pages. References are not counted in the page limit.
Short paper limit: 4 pages. References are not counted in the page limit.

Submissions to SIGIR eCom should be made at

The deadline for paper submission is May 26, 2021 (11: 59 P.M. AoE)