Usage derived recommendations for a video digital library

Bollen, Johan; Nelson, Michael L.; Geisler, Gary; Araujo, Raquel

doi:10.1016/j.jnca.2005.12.009

Cited by 21 publications

(20 citation statements)

References 44 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in the case of only one neighbor is used (Eqs. (1) and (9) in this study), the Resnick's prediction formula may produce out of bounds predictions. To alleviate this issue and maintain the predicted ratings to be within the range of [1,5] in Eqs.…”

Section: A) Trust Derivationmentioning

confidence: 64%

“…More recently, significant steps have been taken in the direction of providing personalized services for a wide variety of web-based applications [3] such as e-business applications [4,5] recommending news [6], movies [7], books [8], videos [9], bundle purchases [10], resource recommendations in social annotation systems [11], and online research papers [12]. Collaborative Filtering (CF) is the best-known recommendation recommender systems technique for producing recommendations, and there are currently a number of popular online companies such as Netflix.com, Amazon.com, and Last.fm that use CF to Researchers have commonly tackled these limitations by incorporating additional external information to the rating information, thereby forming hybrid recommender systems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An effective recommender system by unifying user and item trust information for B2B applications

Shambour

2015

Journal of Computer and System Sciences

View full text Add to dashboard Cite

Although Collaborative Filtering (CF)-based recommender systems have received great success in a variety of applications, they still under-perform and are unable to provide accurate recommendations when users and items have few ratings, resulting in reduced coverage. To overcome these limitations, we propose an effective hybrid user-item trustbased (HUIT) recommendation approach in this paper that fuses the users' and items' implicit trust information. We have also considered and computed user and item global reputations into this approach. This approach allows the recommender system to make an increased number of accurate predictions, especially in circumstances where users and items have few ratings. Experiments on four real-world datasets, particularly a business-to-business (B2B) case study, show that the proposed HUIT recommendation approach significantly outperforms state-of-the-art recommendation algorithms in terms of recommendation accuracy and coverage, as well as significantly alleviating data sparsity, cold-start user and cold-start item problems.

show abstract

Section: A) Trust Derivationmentioning

confidence: 64%

Section: Introductionmentioning

confidence: 99%

An effective recommender system by unifying user and item trust information for B2B applications

Shambour

2015

Journal of Computer and System Sciences

View full text Add to dashboard Cite

show abstract

“…The use of retention actions as a source of implicit relevance feedback has a long history [21,22,23,24,25,26]. Various retention actions used during generic IR were investigated in the literature including:…”

Section: The Use Of Retention Actionsmentioning

confidence: 99%

Design implications for task-specific search utilities for retrieval and re-engineering of code

Iqbal

Halloran

Doctor

et al. 2015

Enterprise Information Systems

View full text Add to dashboard Cite

The importance of information retrieval systems is unquestionable in the modern society and both individuals as well as enterprises recognise the benefits of being able to find information effectively. Current code focused information retrieval systems such as Google Code Search, Codeplex or Koders produce results based on specific keywords and therefore they do not take into account developers' context such as development language, technology/framework, goal of the project, project complexity and maturity or developer's domain expertise. They also impose additional cognitive burden on users in switching between different interfaces and clicking through to find the relevant code. Hence, they are not used by software developers. In this paper, we discuss how software engineers interact with information and general purpose information retrieval systems (e.g. Google, Yahoo) and investigate to what extent domain-specific search and recommendation utilities can be developed in order to support their work related activities. Based on our user studies, we found that software engineers followed many identifiable and repeatable work tasks and behaviours. These behaviours can be used to develop implicit relevance feedback based systems. Based on our results, we discuss the implications for the development of task-specific search and collaborative recommendation utilities embedded with the Google standard search engine and Microsoft IntelliSense for retrieval and reengineering of code. We have implemented a prototype of the proposed collaborative recommendation system which was evaluated in a controlled environment simulating the real world situation of professional software engineers. The evaluation has achieved promising initial results on the precision and recall performance of the system.

show abstract

“…Recommendations, which give advice and suggestions based on a user's prior experience, have been applied in various applications, including digital libraries (e.g. Bollen, Nelson, Geisler, & Araujo, 2007) and electronic business (Liu & Shih, 2005;Shih & Liu, 2008). For example, Cunningham and Frank (1999) developed a recommendation system based on the transaction records of books borrowed from a university library.…”

Section: Related Work 21 Video Summarization and Recommendationmentioning

confidence: 99%

Investigation of learners' perceptions for video summarization and recommendation

Yang

Chen

2012

Interactive Learning Environments

View full text Add to dashboard Cite

Recently, multimedia-based learning is widespread in educational settings. A number of studies investigate how to develop effective techniques to manage a huge volume of video sources, such as summarization and recommendation. However, few studies examine how these techniques affect learners' perceptions in multimedia learning systems. This article aims to examine learners' perceptions for summarization and recommendation, with an emphasis on the perspective of prior experience. In this study, we developed a multimedia content summarization and recommendation system, which can automatically extract summaries from raw video sources and recommend suitable video content to learners through emails. The results demonstrate that learners' prior experience and preferences for the presentation of document types affect their perceptions, including the enhancement of interests, the ease of information acquisition and the intention for the further use of the system. Finally, the findings are applied to develop a framework that can support for the design of multimedia learning systems.

show abstract

Usage derived recommendations for a video digital library

Cited by 21 publications

References 44 publications

An effective recommender system by unifying user and item trust information for B2B applications

An effective recommender system by unifying user and item trust information for B2B applications

Design implications for task-specific search utilities for retrieval and re-engineering of code

Investigation of learners' perceptions for video summarization and recommendation

Contact Info

Product

Resources

About