You are invited to participate in the upcoming DE-PERsonalisation 2018 workshop, that will be held as part of the 40th European Conference on Information Retrieval (ECIR) (https://www.ecir2018.org).
Personalised search gave users significant control over information overload and an ability to simplify the handling of large content collections, such as the web. On the downside, it has led to situations where people find themselves in confined information spaces where similar ideas, beliefs, or data are preserved and repeatedly reinforced to the extent that users find it difficult to retrieve and experience alternative content and competing views. Echo Chambers create substantial polarisation effects, impeding users’ ability to access alternative and diverse information. In search situations, this may disconnect users from others while inside the Echo Chamber, or prevent users from refinding information while outside their Echo Chamber. This one-day workshop aims to explore and host dialogues on the fundamental areas of theory and practice in the domain of de-personalising information spaces and understanding, describing and quantifying filtered information experiences.
Background and Motivation:
Information retrieval (IR) and recommender systems and, more general, approaches in machine learning have resulted in a personalised web experience with resounding success. Building on context, location and users’ virtual (social) profiles, the web is highly aligned to users’ perceived interests, to the interests of ‘similar’ users, and to the interests of users to whom a user is digitally connected. Whilst this delivers relevant content, it also polarises informational perspectives and removes serendipity through the development of Echo Chambers: scenarios where specific ideas, beliefs or data are reinforced through repetition of a closed system that limits the free movement of alternative (competing) ideas. There is the implication that certain ideas or outcomes dominate due to, and resulting in, a bias concerning how specific input is gathered. Under-addressed in the literature are methods to qualify/quantify Echo Chambers and the associated effect(s) they have over time.
The DE-PER Workshop aims to approach the study of Echo Chambers at the intersection of IR, information science, cognitive systems, computational social science, web science, cloud computing, as well as statistics and machine learning to initiate and foster interdisciplinary dialogues on (de-)personalisation for a deeper understanding of filtered information experiences.