Session 7 Thuesday 25, June
Supporting Personalized User Concept Spaces and Recommendations for a Publication Sharing System
Antonina Dattolo, Felice Ferrara, Carlo Tasso
|
| Abstract: Current publication sharing systems weakly support creation and personalization of customized user concept spaces. Focusing the attention on the user and his/her preferences, history, requests, SharingPapers, the adaptive publication sharing system proposed in this paper, allows users to organize documents in flexible and dynamic concept spaces; to merge their conceptual map with a social network connecting people involved in the domain of interest; to support knowledge expansion generating adaptive recommendations. SharingPapers presents a multi-agent architecture and proposes a new way of representing user profiles, their evolution and views of them. |
Evaluating the Adaptation of a Learning System before the Prototype is Ready: A Paper-based Lab Study
Tobias Ley, Barbara Kump, Antonia Maas, Neil Maiden, Dietrich Albert
|
| Abstract: We report on results of a paper-based lab study that used information on task performance, self appraisal and personal learning need assessment to validate the adaptation mechanisms for a work-integrated learning system. We discuss the results in the wider context of the evaluation of adaptive systems where the validation methods we used can be transferred to a work-based setting to iteratively refine adaptation mechanisms and improve model validity. |
Capturing the user’s reading context for tailoring summaries
Cecile Paris, Stephen Wan
|
| Abstract: The web has become a major source of information to learn about a topic. With the continuous growth of information and its high connectivity, it is hard to follow only the links that are relevant and remain focused. Our aim is to support people who read documents in a highly connected information space in order to learn about a topic. In particular, we want to provide them with support to remain on focus. We do this by capturing their interests, by enabling them to obtain contextualised summaries of linked documents to help them decide whether the link is worth following, and, when they decide to follow a link, by reminding them of their interest at the time they opened the document. We present our contextually-aware in-browser text summarisation tool, IBES. |
History dependent Recommender Systems based on Partial Matching
Armelle Brun, Geo ray Bonnin, Anne Boyer
|
| Abstract: This paper focuses on the utilization of the history of navigation within recommender systems. It aims at designing a collaborative recommender based on Markov models relying on partial matching in order to ensure high accuracy, coverage, robustness, low complexity while being anytime. Indeed, contrary to state of the art, this model does not simply match the context of the active user to the context of other users but partial matching is performed: the history of navigation is divided into several subhistories and matching is performed on these subhistories, allowing the matching constraints to be weakened. The resulting model leads to an improvement in terms of accuracy compared to state of the art models. |
Capturing User Intent for Analytical Process
Eugene Santos Jr., Hien Nguyen, John Wilkinson, Fei Yu, Deqing Li, Keum Kim, Jacob Russell, Olson Adam
|
| Abstract: We are working on the problem of modeling an analyst's intent in order to improve collaboration among intelligence analysts. Our approach is to infer the analyst's goals, commitment, and actions to improve the effectiveness in collaborative tasks. This is a crucial problem to ensure successful collaboration because analyst intent provides a deeper understanding of what analysts are trying to achieve and how they are achieving their goals than simply modeling their interests. Without this level of understanding of the analyst's intentions, collaboration may only be suggested based on similarity of topical interests among analysts, which does not reflect the processes behind these interests. The novelty of our approach lies with the modeling the process of committing to a goal as opposed to simply modeling topical interests at specific points in time. Additionally, we dynamically generate the goal hierarchy by exploring the relationships between concepts related to a set of goals. In this short paper, we present the formal framework of our intent model, and demonstrate how it can be used to detect the overlap between analysts' intent using the APEX 07 dataset. |
What Have The Neighbours Ever Done for Us? A Collaborative Filtering Perspective
Rafter Rachael, Michael O'Mahony, Neil Hurley, Barry Smyth
|
| Abstract: Collaborative filtering (CF) techniques have proved to be a powerful and popular component of modern recommender systems. Common approaches such as user-based and item-based methods generate predictions from the past ratings of users by combining two separate ratings components: a point estimate, generally based on the average rating of the target user or item, and a neighbourhood estimate, generally based on the ratings of similar users or items. The common assumption is that the neighbourhood estimate helps to give CF techniques a considerable edge over simpler average-rating techniques. In this paper we examine this assumption more carefully and demonstrate that the influence of neighbours can be surprisingly minor in CF techniques, and we show how this has been disguised by traditional approaches to evaluation, which, we argue, have limited progress in the field. |
|
