Sentimental Analysis of Job Classification using Machine Learning Algorithms
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1279-1284
Abstract
Job classification is done based on work experience, categories with different titles, and salary range. It is the process of classifying and evaluating the job based on responsibilities, duties, and tasks performed. This may change the economic growth for labour and unemployed people. It helps the organization and companies with the requirement and increases the performance of work strength. Job classification is achieved by using machine learning algorithms for classifying. This can be helpful to determine the job in various companies, organizations, and industries. This model’s primary objective is to classify job responsibilities accurately. It concentrates on different parameters (Qualifications, skills, mental capability, experience, individual performance, strengths, etc.) which play a major role in classifying the job. It groups similar jobs based on what it provides requiring the people. According to the Society of Human Resources Management (SHRM), providing a job system can help employers and employees more accurately. These algorithms are used to categorize the job using a variety of machine learning algorithms (Naive Bayes, Random Forest, Decision Tree, KNN, and Support Vector Machine). When compared to other machine learning algorithms, Naive Bayes (94.5%) provides the highest accuracy of the various algorithms. The job classification dataset is used to train and test this model. This model’s primary objective is to categorize jobs according to various factors.Keywords
This publication has 24 references indexed in Scilit:
- Personalized Job Recommendation System at LinkedIn2017
- Effective supervised multiple‐feature learning for fused radar and optical data classificationIET Radar, Sonar & Navigation, 2017
- Machine Learning With Big Data: Challenges and ApproachesIEEE Access, 2017
- Cross-Validated Variable Selection in Tree-Based Methods Improves Predictive PerformanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- AdaBoost and Least Square Based Failure Prediction of Railway Turnouts2016
- Forecasting Obsolescence Risk and Product Life Cycle With Machine LearningIEEE Transactions on Components, Packaging and Manufacturing Technology, 2016
- Random Forests and Kernel MethodsIEEE Transactions on Information Theory, 2016
- Comparison of Advanced Machine Learning Tools for Disruption Prediction and Disruption StudiesIEEE Transactions on Plasma Science, 2013
- Locally linear discriminant analysis for multimodally distributed classes for face recognition with a single model imageIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- A case study of applying boosting naive bayes to claim fraud diagnosisIEEE Transactions on Knowledge and Data Engineering, 2004