Search results for "11"
showing 10 items of 17291 documents
Investigating serendipity in recommender systems based on real user feedback
2018
Over the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-addressed question. According to the most common definition, serendipity consists of three components: relevance, novelty and unexpectedness, where each component has multiple variations. In this paper, we looked at eight different definitions of serendipity and asked users how they perceived them in the context of movie recommendations. We surveyed 475 users of the movie recommender system, MovieLens regarding 2146 movies in total and compared tho…
A Hybrid Multigroup Coclustering Recommendation Framework Based on Information Fusion
2015
Collaborative Filtering (CF) is one of the most successful algorithms in recommender systems. However, it suffers from data sparsity and scalability problems. Although many clustering techniques have been incorporated to alleviate these two problems, most of them fail to achieve further significant improvement in recommendation accuracy. First of all, most of them assume each user or item belongs to a single cluster. Since usually users can hold multiple interests and items may belong to multiple categories, it is more reasonable to assume that users and items can join multiple clusters (groups), where each cluster is a subset of like-minded users and items they prefer. Furthermore, most of…
Cross-Domain Recommendations with Overlapping Items
2016
In recent years, there has been an increasing interest in cross-domain recommender systems. However, most existing works focus on the situation when only users or users and items overlap in different domains. In this paper, we investigate whether the source domain can boost the recommendation performance in the target domain when only items overlap. Due to the lack of publicly available datasets, we collect a dataset from two domains related to music, involving both the users’ rating scores and the description of the items. We then conduct experiments using collaborative filtering and content-based filtering approaches for validation purpose. According to our experimental results, the sourc…
User session level diverse reranking of search results
2018
Most Web search diversity approaches can be categorized as Document Level Diversification (DocLD), Topic Level Diversification (TopicLD) or Term Level Diversification (TermLD). DocLD selects the relevant documents with minimal content overlap to each other. It does not take the coverage of query subtopics into account. TopicLD solves this by modeling query subtopics explicitly. However, the automatic mining of query subtopics is difficult. TermLD tries to cover as many query topic terms as possible, which reduces the task of finding a query's subtopics into finding a set of representative topic terms. In this paper, we propose a novel User Session Level Diversification (UserLD) approach bas…
Open-ended projects opened up — aspects of openness
2017
Abstract—One of the most important areas of competence for professional engineers is the ability to function well in project work, in particular they need to be able to efficiently solve open-ended problems in different collaborative settings. The development of this ability is however not prominent in engineering education despite numerous authors suggesting openended problems as a pedagogical tool to promote development of collaborative problem solving competence by including elements of group or project work in courses. In our own long experience of using open-ended problems in collaborative student projects, we have identified a lack of systematic progression in learning outcomes and sk…
Open Resources as the Educational Basis for a Bachelor-level Project-Based Course
2015
This article presents an innovation-based course concept for project-based learning. In this course, student groups are asked to ideate and implement a software product based on Open Data and Open API releases. By emphasizing studentsâ own product ideation, the course requires and enhances self-directed learning skills and prompts the students to see the unlimited possibilities in becoming and being a practitioner of the computing discipline. Relatedly, the course provides a tool to improve student self-efficacy, as the students, coached through challenges, come to know that they are able to produce software using various open interfaces.
Volkswagen Emission Crisis : Managing Stakeholder Relations on the Web
2016
Organizations establish their own profiles at social media sites to publish pertinent information to customers and other stakeholders. During a long and severe crisis, multiple issues may emerge in media interaction. Positive responses and prompt interaction from the official account of e.g. a car manufacturer creates clarity and reduces anxiety among stakeholders. This research targets the Volkswagen 2015 emission scandal that became public on Sept. 18, 2015. We report its main phases over time based on public web information. To better understand the online interaction and reactions of the company, we scrutinized what information was published on VW’s official web sites, Facebook, and Twi…
Schemata, Acculturation, and Cognition : Expatriates in Japan's Software Industry
2016
This multiple case based empirical study expands the knowledge around North American software and IT workers in Japan as well as the expatriate literature and discussion of cognitive schemata in cross cultural settings. The study includes eleven individuals, nine of them in software. Evidence of selection, rejection, and adjustment of cognitive schemata found in Japan's business world is presented. Changes in schemata drive cultural adjustment and acculturation. North American software and IT workers in Japan must maneuver through unfamiliar and often complex schemata to motivate, lead, manipulate, and communicate with coworkers and partners and thereby gain success.
Understanding Social OER Environments—A Quantitative Study on Factors Influencing the Motivation to Share and Collaborate
2014
Social software environments are increasingly used for open education: teachers and learners share and collaborate in these environments. While there are various possibilities for the inclusion of such social functionalities for OER, many organizational, individual and technological challenges can hinder the motivation of teachers to share and collaborate in these environments. Current research cannot explain what barriers teachers face in social OER environments and how those challenges influence their motivation to engage in such environments. An exploratory factor analysis was used in the context of schools and higher education institutions to investigate the possible barriers to engagin…
Introduction to Innovation, Design, and Analytics Supported Development of ICT Enabled Services Minitrack
2013
Introduction to Innovation, Design, a Analytics Supported Development of ICT Enabled Services Minitrack.