for Journals by Title or ISSN
for Articles by Keywords
Followed Journals
Journal you Follow: 0
Sign Up to follow journals, search in your chosen journals and, optionally, receive Email Alerts when new issues of your Followed Journals are published.
Already have an account? Sign In to see the journals you follow.
Journal Cover Program: Electronic Library and Information Systems
  [SJR: 0.687]   [H-I: 19]   [310 followers]  Follow
   Hybrid Journal Hybrid journal (It can contain Open Access articles)
   ISSN (Print) 0033-0337
   Published by Emerald Homepage  [335 journals]
  • MFS-LDA: a multi-feature space tag recommendation model for cold start
    • Pages: 218 - 234
      Abstract: Program, Volume 51, Issue 3, Page 218-234, September 2017.
      Purpose Tags are used to annotate resources on social media platforms. Most tag recommendation methods use popular tags, but in the case of new resources that are as yet untagged (the cold start problem), popularity-based tag recommendation methods fail to work. The purpose of this paper is to propose a novel model for tag recommendation called multi-feature space latent Dirichlet allocation (MFS-LDA) for cold start problem. Design/methodology/approach MFS-LDA is a novel latent Dirichlet allocation (LDA)-based model which exploits multiple feature spaces (title, contents, and tags) for recommending tags. Exploiting multiple feature spaces allows MFS-LDA to recommend tags even if data from a feature space is missing (the cold start problem). Findings Evaluation of a publicly available data set consisting of around 20,000 Wikipedia articles that are tagged on a social bookmarking website shows a significant improvement over existing LDA-based tag recommendation methods. Originality/value The originality of MFS-LDA lies in segregation of features for removing bias toward dominant features and in synchronization of multiple feature space for tag recommendation.
      Citation: Program
      PubDate: 2017-09-13T08:54:38Z
      DOI: 10.1108/PROG-01-2017-0002
  • Wearable expert system development: definitions, models and challenges for
           the future
    • Pages: 235 - 258
      Abstract: Program, Volume 51, Issue 3, Page 235-258, September 2017.
      Purpose A wearable expert system (WES) is an expert system designed and implemented to obtain input from and give outputs to wearable devices. Among its distinguishing features are the direct cooperation between domain experts and users, and the interaction with a knowledge maintenance system devoted to dynamically update the knowledge base taking care of the evolving scenario. The paper aims to discuss these issues. Design/methodology/approach The WES development method is based on the Knowledge Acquisition Framework based on Knowledge Artifact (KAFKA) framework. KAFKA employs multiple knowledge artifacts, each devoted to the acquisition and management of a specific kind of knowledge. The KAFKA framework is introduced from both the conceptual and computational points of view. An example is given which demonstrates the interaction, within this framework, of taxonomies, Bayesian networks and rule-based systems. An experimental assessment of the framework usability is also given. Findings The most interesting characteristic of WESs is their capability to evolve over time, due both to the measurement of new values for input variables and to the detection of new input events, that can be used to modify, extend and maintain knowledge bases and to represent domains characterized by variability over time. Originality/value WES is a new and challenging concept, dealing with the possibility for a user to develop his/her own decision support systems and update them according to new events when they arise from the environment. The system fully supports domain experts and users with no particular skills in knowledge engineering methodologies, to create, maintain and exploit their expert systems, everywhere and when necessary.
      Citation: Program
      PubDate: 2017-09-13T08:54:46Z
      DOI: 10.1108/PROG-09-2016-0061
  • Why do players purchase in mobile social network games' An examination
           of customer engagement and of uses and gratifications theory
    • Pages: 259 - 277
      Abstract: Program, Volume 51, Issue 3, Page 259-277, September 2017.
      Purpose The purpose of this paper is to explore the purchase intention in mobile social network games (M-SNGs) through a new perspective and discuss how to effectively promote players’ payment. Design/methodology/approach The author proposed a research model by integrating customer engagement (CE) and uses and gratification theory (U&G). Three dimensions of CE and three types of U&G were analyzed, respectively to explore the direct and indirect effects on purchase intention in M-SNGs. Online questionnaires were adopted to collect data, and 354 valid samples were analyzed by structural equation modeling approach. Findings The findings show that hedonic gratification (entertainment) and social gratification (self-presentation) have significant indirect effects on players’ purchase intention in M-SNGs through the mediation effects of CE, whereas this mechanism is not fully applied to utilitarian gratification (flexibility). Besides, three dimensions of CE are not independent, because absorption can indirectly affect vigor through dedication. Research limitations/implications The findings suggest that hedonic gratification (entertainment) and social gratification (self-presentation) can trigger three dimensions of CE to stimulate purchase intentions in M-SNGs, and utilitarian gratification (flexibility) can also promote players’ payment through absorption which is one dimension of CE. Some other theoretical and practical implications are also provided. Originality/value This study is novel in exploring players’ purchase intentions in M-SNGs by integrating CE and U&G. Meanwhile, the author also intends to reveal the relationships among the three dimensions of CE which are related to in-game purchase intention.
      Citation: Program
      PubDate: 2017-09-13T08:54:30Z
      DOI: 10.1108/PROG-12-2016-0078
  • Simultaneous instance and feature selection for improving prediction in
           special education data
    • Pages: 278 - 297
      Abstract: Program, Volume 51, Issue 3, Page 278-297, September 2017.
      Purpose The purpose of this paper is to improve the classification of families having children with affective-behavioral maladies, and thus giving the families a suitable orientation. Design/methodology/approach The proposed methodology includes three steps. Step 1 addresses initial data preprocessing, by noise filtering or data condensation. Step 2 performs a multiple feature sets selection, by using genetic algorithms and rough sets. Finally, Step 3 merges the candidate solutions and obtains the selected features and instances. Findings The new proposal show very good results on the family data (with 100 percent of correct classifications). It also obtained accurate results over a variety of repository data sets. The proposed approach is suitable for dealing with non-symmetric similarity functions, as well as with high-dimensionality mixed and incomplete data. Originality/value Previous work in the state of the art only considers instance selection to preprocess the schools for children with affective-behavioral maladies data. This paper explores using a new combined instance and feature selection technique to select relevant instances and features, leading to better classification, and to a simplification of the data.
      Citation: Program
      PubDate: 2017-09-13T08:54:40Z
      DOI: 10.1108/PROG-02-2016-0014
  • Integrating IR with CRIS – a novel researcher-centric approach
    • Pages: 298 - 321
      Abstract: Program, Volume 51, Issue 3, Page 298-321, September 2017.
      Purpose The purpose of this paper is to present a solution for building an institutional information system (IIS) for the university, so that it combines the functionality of institutional repository (IR) with the functionality of current research information system (CRIS). The paper presents functionality of a system that has been implemented at Warsaw University of Technology (WUT), which solves the requirements of both system types. In addition, applied AI technologies aiming at providing features attractive for the system beneficiaries are presented. Design/methodology/approach The authors have reviewed various approaches to IIS, analyzed the problems observed by researchers in combining CRIS with IR, and have shown how the problems can be solved within a system that integrates various functionalities. Based on this analysis, the authors have implemented software Ω-ΨR (OMEGA-PSIR) for an academic IIS, which integrates requirements of both system types, and then deployed it at WUT. Findings It is shown that although a classical repository is an important part of the CRIS/IR system, the essential value of the solution is in providing analytical tools for “research management.” Based on the example of OMEGA-PSIR, the authors have also presented how the researcher-centric approach influences the acceptance rate of the academic community. It is also shown how the researcher-centric approach can take advantage from integrating the conflicting functionalities of IR and CRIS. Practical implications The paper bridges the gap between theory and practice in the area of IIS for academic institutions. It constructively discusses the role of institutional IR and it provides guides how to develop a system combining functionalities of CRIS and IR, as well as how to make IIS more attractive for the users by making the system researcher centric. Originality/value The survey of various approaches to IIS is unique. The research-centric approach and its implementation within OMEGA-PSIR system are original. Lessons learned from deploying the software at the WUT are of great value for institutions planning to install IR/CRIS solutions. A survey research concerning the system usability is provided, showing practical usefulness of the proposed approach.
      Citation: Program
      PubDate: 2017-09-13T08:54:42Z
      DOI: 10.1108/PROG-04-2017-0026
  • Using Twitter sentiment and emotions analysis of Google Trends for
           decisions making
    • Pages: 322 - 350
      Abstract: Program, Volume 51, Issue 3, Page 322-350, September 2017.
      Purpose An ever-growing body of knowledge demonstrates the correlation among real-world phenomena and search query data issued on Google, as showed in the literature survey introduced in the following. The purpose of this paper is to introduce a pipeline, implemented as a web service, which, starting with recent Google Trends, allows a decision maker to monitor Twitter’s sentiment regarding these trends, enabling users to choose geographic areas for their monitors. In addition to the positive/negative sentiments about Google Trends, the pipeline offers the ability to view, on the same dashboard, the emotions that Google Trends triggers in the Twitter population. Such a set of tools, allows, as a whole, monitoring real-time on Twitter the feelings about Google Trends that would otherwise only fall into search statistics, even if useful. As a whole, the pipeline has no claim of prediction over the trends it tracks. Instead, it aims to provide a user with guidance about Google Trends, which, as the scientific literature demonstrates, is related to many real-world phenomena (e.g. epidemiology, economy, political science). Design/methodology/approach The proposed experimental framework allows the integration of Google search query data and Twitter social data. As new trends emerge in Google searches, the pipeline interrogates Twitter to track, also geographically, the feelings and emotions of Twitter users about new trends. The core of the pipeline is represented by a sentiment analysis framework that make use of a Bayesian machine learning device exploiting deep natural language processing modules to assign emotions and sentiment orientations to a collection of tweets geolocalized on the microblogging platform. The pipeline is accessible as a web service for any user authorized with credentials. Findings The employment of the pipeline for three different monitoring task (i.e. consumer electronics, healthcare, and politics) shows the plausibility of the proposed approach in order to measure social media sentiments and emotions concerning the trends emerged on Google searches. Originality/value The proposed approach aims to bridge the gap among Google search query data and sentiments that emerge on Twitter about these trends.
      Citation: Program
      PubDate: 2017-09-13T08:54:41Z
      DOI: 10.1108/PROG-02-2016-0015
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
Home (Search)
Subjects A-Z
Publishers A-Z
Your IP address:
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-2016