Natural Language Processing Techniques for Analyzing Motivational Letters
Abbas, Qaiser (2024)
2024
Master's Programme in Computing Sciences
Informaatioteknologian ja viestinnän tiedekunta - Faculty of Information Technology and Communication Sciences
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2024-09-11
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202409038519
https://urn.fi/URN:NBN:fi:tuni-202409038519
Tiivistelmä
Motivational letters play a pivotal role in the selection of a candidate in both academic and professional life by providing insights of the applicant educational background, skills, experience and sentiment. In this thesis, we analyzed motivational letters using natural language processing (NLP) techniques to compare and enhance the understanding of the different sentiments and emotions behind the text of AI-generated and Human-written motivational letters.
In this study, we applied different NLP techniques which includes entity recognition, keyword extraction, sentiment analysis, and emotion detection to analyze a set of motivational letters, which divided into two groups, the AI-generated and Human-written motivational letters.
Entity recognition is performed to identify the key entities such as names, organizations, location, qualifications and number of experiences, providing the candidate background information. Keyword extraction plays a significant role in the extraction of the candidate interests and the context of the letters. Sentiment analysis is used to measure the polarity and the subjectivity of the text, which helps in revealing the personal expression and the enthusiasm of the applicant in terms of positive and negative sentiments. Emotion detection is used to identify the emotion of text such as positive, negative, trust, and fear, to further investigate the emotional tone of the motivational letters.
The results of the different motivational letters were compared after the analysis, which revealed the patterns and differences in the context of sentiment and emotion detection scores. The outcomes indicated that most of the AI-generated letters show a positive tone, while some shows low score in terms of emotion tone. On the hand human-written letters demonstrate the higher enthusiasm and confident tone. These findings have a significant role in the application reviewing process and they can be used in the evaluating of motivation letters during selection process of candidates in academics and professional life.
In this study, we applied different NLP techniques which includes entity recognition, keyword extraction, sentiment analysis, and emotion detection to analyze a set of motivational letters, which divided into two groups, the AI-generated and Human-written motivational letters.
Entity recognition is performed to identify the key entities such as names, organizations, location, qualifications and number of experiences, providing the candidate background information. Keyword extraction plays a significant role in the extraction of the candidate interests and the context of the letters. Sentiment analysis is used to measure the polarity and the subjectivity of the text, which helps in revealing the personal expression and the enthusiasm of the applicant in terms of positive and negative sentiments. Emotion detection is used to identify the emotion of text such as positive, negative, trust, and fear, to further investigate the emotional tone of the motivational letters.
The results of the different motivational letters were compared after the analysis, which revealed the patterns and differences in the context of sentiment and emotion detection scores. The outcomes indicated that most of the AI-generated letters show a positive tone, while some shows low score in terms of emotion tone. On the hand human-written letters demonstrate the higher enthusiasm and confident tone. These findings have a significant role in the application reviewing process and they can be used in the evaluating of motivation letters during selection process of candidates in academics and professional life.