Computer Science And Technology - Research Publications

Permanent URI for this collectionhttps://kr.cup.edu.in/handle/32116/82

Browse

Author: search.filters.author.Singh, SatwinderSubject: search.filters.subject.Machine learning

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Comparison of Public and Critics Opinion About the Taliban Government Over Afghanistan Through Sentiment Analysis
    (Springer Science and Business Media Deutschland GmbH, 2023-05-03T00:00:00) Reza, Md Majid; Singh, Satwinder; Kundra, Harish; Reza, Md Rashid
    The usage of social media has increased exponentially these days. People worldwide are sharing their opinions on different platforms such as Twitter, personal blogs, Facebook, and other similar platforms. Twitter has grown in popularity as a platform for people to express their thoughts and opinions on many different topics. The data from Twitter about the Taliban has been examined in this research work, and various machine learning algorithms have been applied including SVM, LR, and random forest. Text sentiments have been captured via TextBlob. Among the machine learning models applied, SVM outperformed all other models and achieved an accuracy score of around 94% on the tweet dataset and logistic regression outperformed other models with an accuracy score of 83% on the news article dataset. � 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Bug Classification Depend Upon Refactoring Area of Code
    (Springer, 2023-01-05T00:00:00) Singh, Satwinder; Jalal, Maddassar; Kaur, Sharanpreet
    Due to rapid development in the software industry, various software is being developed, which compromises the software quality. As long as time passes, the software which compromises with the quality starts showing bugs which adversely affect the working of the software system. Sometimes software undergo repeated addition of functionality, so various classes and functions in software systems become bulky and cause smells in code. Code smells also degrade the software quality, increasing the software system's maintenance cost. So these bad smells should be appropriately detected and eliminated from the software system well on time. With the identification of smells in code, one could easily map the refactoring area of code to improve the code. Improving the code will help in preventive maintenance to identify the bugs quickly. To solve this problem, the current study will focus on the five types of code smells: Data Class, God Class, Feature Envy, Refuse Parent Request and Brain method for identification of bugs in the code. The data set used for this study includes the smell extraction and identification from two versions of Eclipse, i.e. Eclipse 3.6 and Eclipse 3.7, which are renowned open soured industry size software systems. Later on, supervised machine learning classifiers j48, Random Forest, and Naive Bayes are used to identify the bugs in code at the class level. The results show that j48 performed well and provides high accuracy for the identification of bugs with the help of bad smells. � 2023, The Institution of Engineers (India).