Reflection of people's professions on social media platforms

DAĞİSTANLI Ö., Erbay H., KÖR H., Yurttakal A. H.

NEURAL COMPUTING & APPLICATIONS, vol.35, no.7, pp.5575-5586, 2023 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 35 Issue: 7
  • Publication Date: 2023
  • Doi Number: 10.1007/s00521-022-07987-8
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Applied Science & Technology Source, Biotechnology Research Abstracts, Compendex, Computer & Applied Sciences, Index Islamicus, INSPEC, zbMATH
  • Page Numbers: pp.5575-5586
  • Keywords: Holland's theory, Profession, LSTM, GRU
  • Yozgat Bozok University Affiliated: Yes


John Holland asserts that most people are one of the six personality types such as realistic, social, investigative, entrepreneurial, traditional, and artistic. Moreover, he claims that personality is an important factor in career choice, career success, and satisfaction. According to his theory of career choice, people's careers are determined by the interaction between their personality and their environment. The theory points out that people prefer jobs surrounded by others who are like them. It also states that people seek environments that allow them not only to use their skills and abilities but also to express their attitudes and values. On the other hand, people from different professions express their thoughts through Online Social Networks (OSNs). They use social media to express themselves, discuss their interests, connect with friends, and grow their careers. Every day we witness the same person criticizing events in different expertise, such as political events, economic events, etc. Moreover, OSNs connect individuals with like-minded interests and let them share their thoughts, feelings, insights, and emotions. Herein, the reflection of people's profession on OSNs was examined. Inspired by John Holland's theory of career choice, the consistency of personality and work environment would be determined from which an individual's personality can be inferred. In the study, tweets from four different professions: businessman, politician, sportsman, and actor were used to examine whether they are related to the profession. We developed two models using Long Short-Term Memory Neural Networks and Gated Recurrent Unit Neural Networks. The former received macro average accuracy of 94.025% while the latter received 93.025%. According to the simulation results, the proposed models sound and are promising.