In this article, a novel method for personalized item recommendation based on social tagging is presented. The proposed approach comprises a content-based tag propagation method to address the sparsity and "cold start" problems, which often occur in social tagging systems and decrease the quality of recommendations. The proposed method exploits (a) the content of items and (b) users' tag assignments through a relevance feedback mechanism in order to automatically identify the optimal number of content-based and conceptually similar items. The relevance degrees between users, tags, and conceptually similar items are calculated in order to ensure accurate tag propagation and consequently to address the issue of "learning tag relevance." Moreover, the ternary relation among users, tags, and items is preserved by performing tag propagation in the form of triplets based on users' personal preferences and "cold start" degree. The latent associations among users, tags, and items are revealed based on a tensor factorization model in order to build personalized item recommendations. In our experiments with real-world social data, we show the superiority of the proposed approach over other state-of-the-art methods, since several problems in social tagging systems are successfully tackled. Finally, we present the recommendation methodology in the multimodal engine of I-SEARCH, where users' interaction capabilities are demonstrated. ACM Reference Format:Dimitrios Rafailidis, Apostolos Axenopoulos, Jonas Etzold, Stavroula Manolopoulou, and Petros Daras. 2014. Content-based tag propagation and tensor factorization for personalized item recommendation based on social tagging.
Abstract. In this article, a unified framework for multimodal search and retrieval is introduced. The framework is an outcome of the research that took place within the I-SEARCH European Project. The proposed system covers all aspects of a search and retrieval process, namely low-level descriptor extraction, indexing, query formulation, retrieval and visualisation of the search results. All I-SEARCH components advance the state of the art in the corresponding scientific fields. The I-SEARCH multimodal search engine is dynamically adapted to end-user's devices, which can vary from a simple mobile phone to a high-performance PC.
Abstract. Multimodal interaction provides the user with multiple modes of interacting with a system, such as gestures, speech, text, video, audio, etc. A multimodal system allows for several distinct means for input and output of data. In this paper, we present our work in the context of the I-SEARCH project, which aims at enabling context-aware querying of a multimodal search framework including real-world data such as user location or temperature. We introduce the concepts of MuSeBag for multimodal query interfaces, UIIFace for multimodal interaction handling, and CoFind for collaborative search as the core components behind the I-SEARCH multimodal user interface, which we evaluate via a user study.
t t a ) b ) 8 7 ms 8 6 1 ms 3 8 6 ms 8 7 ms 1 3 1 0 ms 3 8 6 msFigure 1: Refinement levels of textured 3D model with (a) our proposed GPUII texture vs. (b) traditional texture (where mesh is transmitted faster, while texture is still loading), both used in combination with X3DOM's progressively streamed geometry (cf. [Limper et al. 2013]). AbstractWe present an adaptive bandwidth-optimized approach for progressive image transmission to allow instant textured rendering in webbased 3D applications. Applications utilizing a lot of image data require an adaptive technology to build responsive user interfaces. This applies especially for the use in mobile networks. While several approaches provide a progressive geometry streaming, they do not focus on a fast and simple texture streaming for 3D web applications. However, standard 2D image transmission technologies are usually inappropriate within a 3D context. In 2D, image size as well as resolution are often set during the authoring phase, whereas in 3D applications size and displayed resolution of textured 3D objects depend on the virtual camera. An adaptive texture transmission mechanism has to consider this as part of its control function. Our approach thus combines progressive texture streaming with an adaptive number of refinement levels without any pixel retransmission. It enables a fast user feedback and reduces the transmitted data to a minimum without loss of visual quality. Moreover, our GPUII approach (GPU-based Image Interlacing) allows an easy integration into existing applications while also reducing the CPU load.
Tools, such as interactive forms, for International Classification of Functioning, Disability and Health (ICF) assessment are expensive to develop, because they are used in different domains and have to be fitted to the special needs of the user groups. This paper focuses on ICF assessment for and by people with dyslexia caused by cognitive impairments. It presents a cost-effective approach to semi-automatically generated, accessible web-forms. Based on a developed meta-model enriched with so called clarifying communication elements and state information, a system was developed, which transforms the model at runtime into an interactive web application. Every text element of the form can on the one hand be personalized and on the other hand can be enhanced with available content like icons, images, videos showing explanations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.