Sihem Amer-Yahia (CNRS - SLIDE, France) is a CNRS Research Director in Grenoble where she leads the SLIDE team.
Her interests are at the intersection of large-scale data management and data analytics. Before joining CNRS, she was Principal Scientist at QCRI, Senior Scientist at Yahoo! Research and Member of Technical Staff at at&t Labs.
Sihem served on the SIGMOD Executive Board, the VLDB Endowment, and the EDBT Board. She is Editor-in-Chief of the VLDB Journal. Sihem is PC co-chair for VLDB 2018, WWW 2018 Toturials and ICDE 2019 Tutorials.
Sihem received her Ph.D. in CS from Paris-Orsay and INRIA in 1999, and her Diplôme d’Ingénieur from INI, Algeria.
While personalization is useful, current algorithms confine users into profiles that reflect their most predominant characteristics, while ignoring their other characteristics, such as their hidden or evolving interests.
This can be addressed by allowing users to intervene and examine two cases of intervention: Customization and Adaptive Personalization. We show the benefit of letting users interact with personalized travel packages to find their hidden interests (DSAA 2017). We also examine adaptive task assignment in crowdsourcing that relies on observing workers as they complete tasks and capturing their evolving motivation (EDBT 2017).
The last part of the talk speculates on how far we can push human-in-the-loop personalization to please different humans.
This work is in collaboration with Shady Elbassuoni, Prof. at AUB (Lebanon) and with Senjuti Basu Roy, Prof. at NJIT (USA)
Denis Parra is Assistant Professor at the Department of Computer Science, in the School of Engineering at PUC Chile.
He obtained his Ph.D. in Information Science from University of Pittsburgh, USA.
His main research interests are Recommender Systems, Intelligent User Interfaces and Information Visualization.
He has published in important conferences in the area such as RecSys, IUI, UMAP, ECIR and Hypertext as well as in journals such as EPJ, PloS One, IJHCS, ESWA, and ACM TiiS.
He is currently leading the SocVis Lab at PUC Chile.
Social aspects in Interactive Recommender Systems: Bridging the gap between predictive algorithms and interactive user interfaces.
Recommender systems have been researched extensively over the past decades. Much of this reseach have focused on algoriths optimized for accuracy and ranking, deployed in various application domains, but recent research efforts are increasingly oriented towards the user experience of recommender systems.
This research goes beyond accuracy of recommendation algorithms and deals with various human factors that affect acceptance of recommendations, such as user satisfaction, trust, transparency and sense of control.
In this talk, Prof. Parra describes several works on interactive visualizations for recommender systems and introduces a framework that combines recommendation with visualization techniques to support human-recommender interaction.
Then, the interactive recommender systems are contextualized over the dimensions of the framework, providing details on Prof. Parra's work such as TalkExplorer, SetFusion, Moodplay and EpistAid.
The work is highlighted within the workshop's goal: social aspects in interactive recommendation systems. Finally, Prof. Parra presents future research challenges and opportunities in this area.
Call for Papers:
In order to improve the web experience of the users, classic personalization technologies (e.g., recommender systems) and search engines usually rely on static schemes. Indeed, users are allowed to express ratings in a fixed range of values for a given catalogue of products, or to express a query that usually returns the same set of webpages/products for all the users.
With the advent of communication systems (social media platforms, instant messaging systems, speech recognition and transcription tools, etc.), users have been allowed to create new content and to express opinions and preferences in new forms (e.g., likes, textual comments, and audio feedbacks). Moreover, the social interactions can provide information on who influences whom. Being able to mine usage and collaboration patterns that arise thanks to social aspects and to analyze the collective cooperations, opens new frontiers in the generation of personalization services and in the improvement of search engines. Moreover, recent technological advances, such as deep learning, are able to provide a context to the analyzed data (e.g., word embeddings provide a vector representation of the words in a corpus, considering the context in which a word has been used).
Our workshop will solicit contributions in all topics related to employing social aspects for personalization and search purposes, focused (but not limited) to the following list:
- Recommender systems;
- Search and tagging;
- Query expansion;
- User modeling and profiling;
- Advertising and ad targeting;
- Content classification, categorization, and clustering;
- Using social network features/community detection algorithms for personalization and search purposes;
- Employing speech transcription in personalization and search;
- Building benchmarking datasets;
- Novel evaluation methodologies in the social context;
Types of contribution:
We will consider three different submission types, all in the LNCS format: regular (14 pages), short (6 pages) and extended abstracts (4 pages).
Research and position papers (regular or short) should be clearly placed with respect to the state of the art and state the contribution of the proposal in the domain of application, even if presenting preliminary results. In particular, research papers should describe the methodology in detail, experiments should be repeatable, and a comparison with the existing approaches in the literature should be made where possible.
Position papers (short) should introduce novel point of views in the workshop topics or summarize the experience of a researcher or a group in the field.
Practice and experience reports (short) should present in detail the real-world scenarios in which social aspects are employed for personalization and search purposes.
Demo proposals (extended abstract) should present the details of a prototype or complete application that employs social aspects for personalization and search purposes. The systems will be demonstrated to the workshop attendees.
The reviewing process will be coordinated by the organizers. Each paper will receive three reviews: two externals to the organizing committee and one internal. The external reviewers will be contacted according to their expertise in the paper topic.
All submission must be written in English and follow the ECIR paper guidelines. All papers must be formatted according to the LNCS format style. Papers should be submitted in PDF format, electronically, using the EasyChair submission system, available at: SoAPS@EasyChair (please, select track “Workshop on Social Aspects in Personalization and Search" when creating a new submission)
All accepted papers will be made available on the workshop website together with the material generated during the meeting.
Revised selected papers will be published as a post-proceedings in a LNCS volume, published by Springer.Authors of selected papers will also be invited to submit an extended version in a journal special issue.