Recommender systems are acknowledged as an essential instrument to support users in finding relevant information in an overloaded information space. While they have been proven successful in e.g., e-commerce applications, they can also support organizations in better identifying competences, help engage users in a continuous and dynamic knowledge exchange, and customize dissemination of knowledge as much as possible. Moreover, the advent of the big data era has posed the need for high scalability and real-time processing of frequent data updates, and thus, has brought new challenges for the recommender systems’ research community. As in 2016 (http://socialcomputing.know-center.tugraz.at/rs-bda/), the objective of this workshop is to bring together researchers and practitioners involved in developing, testing, and maintaining (social) recommender systems, especially in the light of big data. The workshop focuses on all aspects of recommender systems and big data analytics and it will provide a forum for discussing current practices and recent research results. RS-BDA'17 is co-located with i-KNOW 2017 (http://i-know.tugraz.at/).
The program of the workshop will consist of invited and accepted paper talks.
Authors of papers have 20 minutes dedicated for presenting their work and 10 minutes allocated for discussion.
Title: Using Chusapedia to Design Applications That Support Human Choice
Anthony Jameson is a Principal Researcher at DFKI, the German Research Center for Artificial Intelligence and founder of the new startup Chusable AG, which specializes in software for helping people to make better choices. Since the late 1970s, he has done research and practical work on various types of interactive intelligent system, combining knowledge of psychology, artificial intelligence, and human-computer interaction. From 2009-2016 he was founding coeditor-in-chief of the ACM Transactions on Interactive Intelligent Systems. Work especially related to the Chusapedia system presented at i-KNOW 2017 includes (a) the theoretical integration of research on choice and choice support expounded in the 2014 book Choice Architecture for Human-Computer Interaction and in the handbook chapter Human Decision Making and Recommender Systems; and (b) work on systems that integrate knowledge using semantic technology: participation in Project Halo; and the leadership of 3cixty, which won the 2015 Semantic Web Challenge.Abstract
With special attention to applications to recommender systems, this brief tutorial offers an introduction to the web-based system Chusapedia (introduced in a different context in the Wednesday morning keynote titled “Human Choices in Smart Production”).
The overall function of Chusapedia is to help analysts design interactive systems – and, more generally, complete interventions – that help people to make better choices. In this context, recommendation technology is viewed as one the most directly relevant of a number of technologies that can be leveraged in choice-supporting interventions.
Chusapedia makes use of a continually extensible repository of knowledge about human choice and choice support, which is derived from a wide range of research literature and practical experience.
The tutorial will address the following questions:
Participants who would like to try Chusapedia out briefly during the tutorial should bring along a tablet or laptop with internet access. All participants will be able to access Chusapedia after the tutorial and to use it independently.
Signed Graph Analysis for the Interpretation of Voting Behavior
Nejat Arinik, Rosa Figueiredo and Vincent Labatut
Studo Jobs: Enriching Data With Predicted Job Labels
Markus Reiter-Haas, Valentin Slawicek and Emanuel Lacic
OpenReq: Recommender Systems in Requirements Engineering
Alexander Felfernig, Martin Stettinger, Andreas Falkner, Müslüm Atas, Xavier Franch and Cristina Palomares
The main topic of this workshop is the broad research area of recommender systems and how it is connected with big data analytics. Thus, it is our main intention to bring together researchers and practitioners in these areas to discuss novel trends in analyzing big data for recommender systems. This workshop theme should be of great interest for i-KNOW 2017 attendees since both recommender systems and big data analytics are important research instruments at the intersection of the disciplines of knowledge discovery, Web & data science as well as social computing.
Overall topics to be adressed by this workshop include but are not limited to:
Within these topics, we encourage demo papers (max. 2 pages), short research papers (max. 4 pages) and long research papers (max. 8 pages), both in ACM double-column conference paper style. All submitted papers must:
All papers will be peer-reviewed and must not be under review in any other conference, workshop or journal. Accepted full papers will be published in the ACM Digital Library and papers accepted as short/demo will be optionally published in special online workshop proceedings.