User modeling

About: User modeling is a research topic. Over the lifetime, 10701 publications have been published within this topic receiving 278012 citations.

Method and system for personalized segmentation and indexing of media

Abstract: This disclosure describes systems, methods and user interfaces that allow a user to identify, annotate and share a portion of a media item with another user. Through the user interface, the user may render a media item and identify a segment of the media item. Based on the media item, previously defined and shared segments may be suggested to the user allowing the user to quickly select and identify popular segments for sharing. In addition, previously used annotations of previously defined and shared segments may be suggested to the user allowing users to quickly select annotations. The sharing user may then issue a command that causes a link or other means for accessing the segment to be transmitted to a recipient. Accessing this link or other means, causes the segment defined by the sharing user to be rendered on the recipient's device.

Interest-aware Message-Passing GCN for Recommendation

Abstract: Graph Convolution Networks (GCNs) manifest great potential in recommendation. This is attributed to their capability on learning good user and item embeddings by exploiting the collaborative signals from the high-order neighbors. Like other GCN models, the GCN based recommendation models also suffer from the notorious over-smoothing problem – when stacking more layers, node embeddings become more similar and eventually indistinguishable, resulted in performance degradation. The recently proposed LightGCN and LR-GCN alleviate this problem to some extent, however, we argue that they overlook an important factor for the over-smoothing problem in recommendation, that is, high-order neighboring users with no common interests of a user can be also involved in the user’s embedding learning in the graph convolution operation. As a result, the multi-layer graph convolution will make users with dissimilar interests have similar embeddings. In this paper, we propose a novel Interest-aware Message-Passing GCN (IMP-GCN) recommendation model, which performs high-order graph convolution inside subgraphs. The subgraph consists of users with similar interests and their interacted items. To form the subgraphs, we design an unsupervised subgraph generation module, which can effectively identify users with common interests by exploiting both user feature and graph structure. To this end, our model can avoid propagating negative information from high-order neighbors into embedding learning. Experimental results on three large-scale benchmark datasets show that our model can gain performance improvement by stacking more layers and outperform the state-of-the-art GCN-based recommendation models significantly.

Predicting web actions from HTML content

Abstract: Most proposed Web prefetching techniques make predictions based on the historical references to requested objects. In contrast, this paper examines the accuracy of predicting a user's next action based on analysis of the content of the pages requested recently by the user. Predictions are made using the similarity of a model of the user's interest to the text in and around the hypertext anchors of recently requested Web pages. This approa22ch can make predictions of actions that have never been taken by the user and potentially make predictions that reflect current user interests. We evaluate this technique using data from a full-content log of Web activity and find that textual similarity-based predictions outperform simpler approaches.

Systems and methods for displaying text recommendations during collaborative note taking

Abstract: Multiple users access a collaborative data-sharing system during a data-sharing event Each user can establish the level of sharing to be allowed with each other user and filtering criteria for filtering the data before it is provided to the other users Data can be extracted from a number of different sources, including data input by other users and/or previously created information sources For example, slides from a presentation on a similar topic may be identified and included by a user as a potential source of information to be used by other users Shared data can be displayed on devices used by users to communicate with the collaborative data-sharing system A user can selected data provided by the collaborative data-sharing system, which was obtained from the data input by other users and/or from the identified additional data sources and added to that user's data as data entered by that user