6. Workshop Programme


09.00—09.15  Welcome 

09.1510.15 Keynote presentation

    Peter Brusilovsky: "Personalization in the Context of Relevance-Based Visualisation"

Relevance-based visualization is a popular information visualization approach that attempts to visualize a set of items in a form that stresses their relevance to different aspects of user interests. Relevance-based visualization has been originally developed in the field of information retrieval for visualization of search results. The idea of relevance visualization in this context was to stress visually which results were relevant to different terms in a complex multi-term queries. For example, the classic TileBars system (Hearst 1995) augmented each result in a traditional ranked list with a “tile bar” that visualized a match between document fragments and each of the query keywords. In this talk, I will review our research attempts to implement different kinds of personalization in the context of relevance-based visualization. The goal of this research stream is to make relevance-based visualization adaptive to user long-term goals, interests, or prospects rather just responsive to short term immediate needs such as query terms. I will present four personalized relevance-based visualization systems developed in our research team as well as in collaboration with Katrien Verbert’s team in Catholic University Leuven: Adaptive VIBE (Ahn and Brusilovsky 2013), TalkExplorer (Verbert, 2016), SetFusion (Parra, 2015), and IntersectionExplorer (Verbert, 2016). For each system, I will present its idea, some evaluation results, and lessons learned.

10.15—10.45 Coffee break

10.45—12.15 Oral Presentations
  1.  E. Palagi, F. Gandon, A. Giboin, and R. Troncy.  A Survey of Definitions and Models of Exploratory Search.
  2.  L. Shao, N. Silva, E. Eggeling, and T. Schreck. Visual Exploration of Large Scatter Plot Matrices by Pattern Recommendation based on Eye Tracking.
  3.  S. Yogev, G. Shani, and N. Tractinsky. HiveRel: Towards Focused Knowledge Acquisition.
  4.  C. Christodoulakis, E. Kandogan, I. G. Terrizzano, and R. J. Miller. VIQS: Visual Interactive Exploration of Query Semantics.
  5.  P. Hasitschka and V. Sabol. Visual Exploration and Analysis of Recommender Histories.
12.15—13.30 Lunch

13.3014.30 Keynote presentation

     Eduardo Veas: "From Search to Discovery with Visual Exploration Tools"

In our goal to personalize the discovery of scientific information, we built systems using visual analytics principles for exploration of textual documents. The concept was extended to explore information quality of user generated content. Our interfaces build upon a cognitive model that recognizes awareness key step of the exploration process. In education-related circles, a frequent concern is that people increasingly need to know how to search, and that knowing how to search leads to finding information efficiently. The ever-growing information overabundance right at our fingertips needs a natural skill to develop and refine search queries to get better search results, or does it? Exploratory search is an investigative behaviour we adopt to build knowledge by iteratively selecting interesting features that lead to associations between representative items in the information space. Formulating queries was proven more complicated for humans than recognizing information visually. Visual analytics takes the form of an open ended dialog between the user and the underlying analytics algorithms operating on the data. This talk describes studies on exploration and discovery with visual analytics interfaces that emphasize transparency and control features to trigger awareness. We will discuss the interface design and the studies of visual exploration behavior.

14.30—15.00 Oral Presentation & Lightning talks
       6.  C. di Sciascio, L. Mayr, and E. Veas. Adaptive visual exploration for scientific paper writing.
  •  Lightning presentations of posters (1 slide, 2min each)
15.00—15.30 Coffee break

15.30—16.30 Poster session
  1. H. Afrabandpey, T. Peltola, and S. Kaski. Improving Small Sample Size Prediction By Interactive Prior Elicitation of Features Pairwise Similarities.
  2. H. Fujino and K. Hasida. Music Exploration by Impression Based Interaction.
  3. A. Sorkhei, K. Ilves, and D. Głowacka. Exploring Scientific Literature Search Through Topic Models
  4. L. Huang, S. Matwin, E. De Carvalho, and R. Minghim. Active Learning with Visualization for Text Data.
  5. D. Kosmajac, V. Keselj, and E. Milios. Text visualisation at the level of N–grams based on Eulerian graphs.
  6. J. Guerra, C. Catania, and E. Veas. Visual exploration of network hostile behavior. 
16.3017.30 Panel discussion
  • Eduardo Veas University of Cuyo, Argentina; Know-Center, Austria
  • Peter Brusilovsky University of Pittsburgh, USA
  • Dorota Glowacka University of Helsinki, Finland
  • Denis Parra PUC, Chile 
  • Shlomo Berkovsky CSIRO, Australia
  • Kevin McCurley Google, USA