Software Bug Reports: Automatic Keyword and Sentence-Based Text Summarization Using Artificial Intelligence
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2022, Vol 10, Issue 6
Abstract
The purpose of text summarization is to quickly and accurately extract the most important data from papers. The proposed unsupervised method seeks to synthesise complete and informative bug reports (software artefacts). The suggested approach employs Rapid Auto- matic Keyword Extraction and the term frequency-inverse document frequency method to identify applicable keywords and phrases. During the sentence extraction procedure, fuzzy C-means clustering is used to prioritise sentences that have a high degree of membership in each cluster (beyond a predefined threshold). The selection of sentences is performed by a rule-engine. Information is extracted using keywords and sentences chosen by the clustering process, and the rules are developed using domain knowledge. The proposed method produces a logical and well-organized summary of apache bug reports. The retrieval summary is improved with the help of hierarchical clustering by removing unnecessary details and rearranging them. The Apache Project Bug Report Corpus (APBRC) and the original Bug Report Corpus are used to evaluate the effectiveness of the proposed method. Measures of performance such as precision, recall, pyramid precision, and F-score are used to evaluate the results. Experiment results demonstrate that our proposed method significantly outperforms the state-of-the-art baseline methods like BRC and LRCA. In addition, it achieves substantial gains compared to prior art unsupervised methods as Hurried and centroid. It extracts the most relevant keyword phrases and sentences from each cluster to offer comprehensive coverage and a coherent summary. The average values for precision, recall, f-score, and pyramid precision on the APBRC corpus are 78.22%, 82.18%, 80.10%, and 81.66%, respectively.
Authors and Affiliations
Zaid Altaf, and Ashish Oberoi
Keywords
Related Articles
- EP ID EP746018
- DOI 10.55524/ijircst.2022.10.6.18
- Views 54
- Downloads 0
A Review on Black Hole Detection on Mobile Ad-hoc Network
MANET is a network with unrestricted mobility in nature and no centralised control. Mobile node can move from one network to another frequently. MANET is infrastructure less so any node can enter and exit the system at a...
Customer Churn Prediction in Telecom Industry Using Regression Algorithms
Customer acquisition and retention is a major challenge in a variety of industries, but it is most severe in highly competitive and fast-growing companies. Customer turnover is a major worry for large organisations since...
A New Security Primitive Based on Hard AI Problems and Efficient User Authentication using Captcha and Graphical Passwords
In this paper,I present a new security primitive based on hard AI (Artificial Intelligence) problems, namely, a novel family of graphical password systems built on top of Captcha technology, which we call Captcha as grap...
Review on Teaching Ethical Hacking
The word hacker generally characterize the practice or performance of investigating & carry out trial with computer networks as computer communications grew more ubiquitous with the emergence of the Internet. However, wh...
Hybrid Active Power Filter for Power Quality Improvement
A Deadbeat current controller for an LC-coupling hybrid active power filter is proposed, which can track with the reference compensation current with low steady- state error and fast dynamic response. Moreover, it can le...