Assessing Institutional Performance Using Machine Learning Algorithms
In Middle Eastern nations, social media has grown in importance in influencing political and governmental choices. In Iraq, Facebook is regarded as one of the most widely used social networking sites. The underutilization of this tool for evaluating institutional performance persists. Thus, using s...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
College of Computer and Information Technology – University of Wasit, Iraq
2024-09-01
|
| Series: | Wasit Journal of Computer and Mathematics Science |
| Subjects: | |
| Online Access: | http://wjcm.uowasit.edu.iq/index.php/wjcm/article/view/263 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582130042929152 |
|---|---|
| author | zainabalwan anwer Ahmad Abdalrada Ihtiram Raza Khan |
| author_facet | zainabalwan anwer Ahmad Abdalrada Ihtiram Raza Khan |
| author_sort | zainabalwan anwer |
| collection | DOAJ |
| description |
In Middle Eastern nations, social media has grown in importance in influencing political and governmental choices. In Iraq, Facebook is regarded as one of the most widely used social networking sites. The underutilization of this tool for evaluating institutional performance persists. Thus, using sentiment analysis on Facebook, this study suggests a methodology that aids organizations like the Ministry of Justice in Iraq in assessing their own performance. The model makes use of a variety of machine learning methods, including Naive Bayes, Logistic Regression, and Support Vector Machine. TF-IDF (Term Frequency-Inverse Document Frequency) was used to convert the textual data into numerical features, which is essential for effective text analysis. Additionally, features were carefully managed by utilizing both unigram and bigram models. Using datasets from (Facebook pages belonging to the Iraqi Ministry of Justice), a thorough experimental investigation was conducted. The results of our experiments showed that the SVM algorithm produced the best accuracy, at 98.311%. following the suggested model's retention of a few stop words, which was shown to significantly improve the algorithm's performance and guarantee accurate categorization of comments while maintaining the content of the phrase.
|
| format | Article |
| id | doaj-art-dca83381653e4582a29c8961cf79de4c |
| institution | Kabale University |
| issn | 2788-5879 2788-5887 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | College of Computer and Information Technology – University of Wasit, Iraq |
| record_format | Article |
| series | Wasit Journal of Computer and Mathematics Science |
| spelling | doaj-art-dca83381653e4582a29c8961cf79de4c2025-01-30T05:23:47ZengCollege of Computer and Information Technology – University of Wasit, IraqWasit Journal of Computer and Mathematics Science2788-58792788-58872024-09-013310.31185/wjcms.263Assessing Institutional Performance Using Machine Learning Algorithmszainabalwan anwer0Ahmad Abdalrada1Ihtiram Raza Khan2Department of Software, Faculty of Computer Science and Information Technology, Wasit University, IraqDepartment of Software, Faculty of Computer Science and Information Technology, Wasit University, IraqDepartment of Computer Science & Engineering, School of Engineering Sciences & Technology Jamia Hamdard Delhi, India In Middle Eastern nations, social media has grown in importance in influencing political and governmental choices. In Iraq, Facebook is regarded as one of the most widely used social networking sites. The underutilization of this tool for evaluating institutional performance persists. Thus, using sentiment analysis on Facebook, this study suggests a methodology that aids organizations like the Ministry of Justice in Iraq in assessing their own performance. The model makes use of a variety of machine learning methods, including Naive Bayes, Logistic Regression, and Support Vector Machine. TF-IDF (Term Frequency-Inverse Document Frequency) was used to convert the textual data into numerical features, which is essential for effective text analysis. Additionally, features were carefully managed by utilizing both unigram and bigram models. Using datasets from (Facebook pages belonging to the Iraqi Ministry of Justice), a thorough experimental investigation was conducted. The results of our experiments showed that the SVM algorithm produced the best accuracy, at 98.311%. following the suggested model's retention of a few stop words, which was shown to significantly improve the algorithm's performance and guarantee accurate categorization of comments while maintaining the content of the phrase. http://wjcm.uowasit.edu.iq/index.php/wjcm/article/view/263Sentiment analysisSocial mediaMachine Learning AlgorithmsTF-IDF |
| spellingShingle | zainabalwan anwer Ahmad Abdalrada Ihtiram Raza Khan Assessing Institutional Performance Using Machine Learning Algorithms Wasit Journal of Computer and Mathematics Science Sentiment analysis Social media Machine Learning Algorithms TF-IDF |
| title | Assessing Institutional Performance Using Machine Learning Algorithms |
| title_full | Assessing Institutional Performance Using Machine Learning Algorithms |
| title_fullStr | Assessing Institutional Performance Using Machine Learning Algorithms |
| title_full_unstemmed | Assessing Institutional Performance Using Machine Learning Algorithms |
| title_short | Assessing Institutional Performance Using Machine Learning Algorithms |
| title_sort | assessing institutional performance using machine learning algorithms |
| topic | Sentiment analysis Social media Machine Learning Algorithms TF-IDF |
| url | http://wjcm.uowasit.edu.iq/index.php/wjcm/article/view/263 |
| work_keys_str_mv | AT zainabalwananwer assessinginstitutionalperformanceusingmachinelearningalgorithms AT ahmadabdalrada assessinginstitutionalperformanceusingmachinelearningalgorithms AT ihtiramrazakhan assessinginstitutionalperformanceusingmachinelearningalgorithms |