Welcome to the InfoSci Platform
Heterogeneous Weighted Voting-Based Ensemble (HWVE) for Root-Cause Analysis

Heterogeneous Weighted Voting-Based Ensemble (HWVE) for Root-Cause Analysis

Blessy Selvam, Ravimaran S., Sheba Selvam
Copyright: © 2020 |Volume: 13 |Issue: 4 |Pages: 12
ISSN: 1938-7857|EISSN: 1938-7865|EISBN13: 9781799805489|DOI: 10.4018/JITR.2020100105
Cite Article Cite Article

MLA

Selvam, Blessy, et al. "Heterogeneous Weighted Voting-Based Ensemble (HWVE) for Root-Cause Analysis." JITR vol.13, no.4 2020: pp.63-74. http://doi.org/10.4018/JITR.2020100105

APA

Selvam, B., Ravimaran S., & Selvam, S. (2020). Heterogeneous Weighted Voting-Based Ensemble (HWVE) for Root-Cause Analysis. Journal of Information Technology Research (JITR), 13(4), 63-74. http://doi.org/10.4018/JITR.2020100105

Chicago

Selvam, Blessy, Ravimaran S., and Sheba Selvam. "Heterogeneous Weighted Voting-Based Ensemble (HWVE) for Root-Cause Analysis," Journal of Information Technology Research (JITR) 13, no.4: 63-74. http://doi.org/10.4018/JITR.2020100105

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Root-cause analysis has been one of the major requirements of the current information-rich world due to the huge number of opinions available online. This paper presents a heterogeneous weighted voting-based ensemble (HWVE) model for root-cause analysis. The proposed model is composed of an aspect extraction and filtering module, a model-based sentiment identification module, and a ranking module. Domain-based aspect ontologies are created using the available training data and is used for categorization. The input data is passed to the HWVE model for opinion identification and is in-parallel passed to the significance identification phase for aspect identification. The identified aspects are combined with their corresponding sentiments and ranked based on their ontological occurrence levels to provide the final categorized root-causes. Experiments were performed with the five-product dataset, and comparisons were performed with recent models. Results indicate that the proposed model exhibits improved performances of 5%-13% in terms of F-measure when compared to other models.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.