A Plausible RNN-LSTM based Profession Recommendation System by Predicting Human Personality Types on Social Media Forums

Personality is a unique combination of attributes that affect ideas, feelings, and behaviors. Some personality factors predict both professional success and antisocial behavior at work, according to research studies. More than 80% of Fortune 500 companies use personality tests for job screening, leadership development and team building. On the other side, due to increased internet availability, more people are self-expressing and socializing online. Particularly, Twitter, one of the most advanced social networking platforms, generates terabytes of data every day. As a result, current research studies are looking into whether online profiles and actions can reveal people's personalities. The RNN-LSTM-based Profession Recommendation System (RNN-PRS) is proposed to investigate the user's character from their social media activity by using MBTI and recommends suitable professions. In the first stages of development, RNN-PRS places primary emphasis on the collection of character-specific data. Following that, RNN-PRS performs a series of pre-processing techniques to clean up the data obtained from the dataset and get it ready for further processing. After processing, the dataset is split into training and testing portion. When training the model, k-fold cross-validation is used on the dataset with varying values of k. The RNN-PRS learning method implements RNN-LSTM learning technique in the following stage to create the final model. The cross-validation method uses test data to validate the performance of the trained model. The completed model is then evaluated using test data produced during the pre-processing stage to determine the accuracy learning algorithm. In the result analysis, the model investigates its performance over KNN, Logistic Regression, Naive Bayes and Support Vector Machine. A case study is also performed on the Twitter data to recommend a suitable profession based on their personality type. Both job seekers and hiring managers might benefit from the findings of this study in terms of narrowing down their options to the most suitable profession.