Subjects: Psychology >> Applied Psychology Subjects: Computer Science >> Computer Application Technology submitted time 2024-02-29
Abstract： Objective With the development of network big data and machine learning, more and more studies starting to combine text analysis and machine learning algorithms to predict individual satisfaction. In the studies focused on building life satisfaction prediction models, it is often difficult to obtain large amounts of valid and labeled data. This study aims at solving this problem using data augmentation and optimizing the prediction model of life satisfaction. Method Using 357 life status descriptions annotated by self-rating life satisfaction scale scores as original text data. After preprocessing using DLUT-Emotionontology, EAD and back-translation method was applied and the prediction model was built using traditional machine learning algorithms. Results Results showed that (1) the prediction accuracy was largely enhanced after using the adapted version of DLUT-Emotionontology; (2) only linear regression model was enhanced after data augmentation; (3) rigid regression model showed the greatest prediction accuracy when trained by original data (r = 0.4131). Conclusion The improvement of feature extraction accuracy can optimize the current life satisfaction prediction model, but the text data augmentation methods, such as back translation and EDA may not be applicable for the life satisfaction prediction model based on word frequency.
Peer Review Status:
Awaiting Review
Subjects: Psychology >> Applied Psychology submitted time 2022-10-18
Abstract： The campus life of college students has undergone a tremendous change since the outbreak of COVID-19. Due to the constant adjustment of the policy, the closure of schools and dormitories, students’ communication and leisure activities are restricted, so their mood fluctuates, which cannot be fully reflected by traditional scales. College students live a group life, their mentality has social and group attributes, whose formation and change involve many factors and is not simply the accumulation and mechanical superposition of individual mindsets. The Population Mental Health Measurement (DASS) tends to be the measurement when negative emotions are severe, so it cannot fully express the “positive” attitude when the epidemic is getting better.SCL-90 (90 Symptom Checklist) and SDS (Depression Status Scale) usually tend to measure individuals rather than studies on risk perception and psychological behavior. After research, the mental awareness scale during the COVID-19 was prepared and tested. Our research has positive implications for the public’s mental perception under COVID-19. Only by understanding the changes in the mindset of the public can we carry out targeted psychological counseling and win the people’s war against the epidemic.
Peer Review Status:Awaiting Review
Subjects: Psychology >> Applied Psychology submitted time 2022-03-18
Abstract：
This paper introduces the big data research method in psychology in details, taking Ninety-Nine Articles website as an example. Using the collected textual data, we calculated word frequencies as features, then trained machine learning models, and used models to predict life satisfaction for texts crawled from Ninety-Nine Articles website, providing inspiration and help for beginners in big data research. This paper introduces text-based word frequency calculation using Python and sentiment dictionary through specific examples, and completes the training, testing and application of the machine learning model using Python's scikit-learn library. Furthermore, we uploaded the accompanying source program for direct operation. This paper introduces the big data research method of machine learning modeling via text-based word frequency. Our article emphasizes how to apply the technology, and thus we introduce the technology in a more basic way with less involvement of the technical principles.
Peer Review Status:Awaiting Review
Subjects: Psychology >> Applied Psychology submitted time 2022-03-06
Abstract：
In order to explore the differences in life satisfaction and emotional word frequency between single people and married people, this study uses Python to collect data from Zhihu, China’s largest Q&A platform, and obtain the corresponding group's sentiment frequency ratio through the "Wenxin" system and life satisfaction score by a life satisfaction prediction model. Results showed that the life satisfaction score in the married group was significantly higher than that in the single group (t=4.415, p<0.001); The proportion of positive emotion words (t=-9.061, p<0.001) and anxiety words (t=1.844, p<0.001) in the married group was significantly lower than that in the single group, but the proportion of anger words (t=5.101, p<0.001) was significantly higher than that in the single group. The results show that while married people obtain higher life satisfaction and lower anxiety level, they also need to deal with partner related emotional problems."
Peer Review Status:Awaiting Review
Subjects: Psychology >> Applied Psychology submitted time 2022-03-06
Abstract：
[Objective] To explore the impact of coming out or not on the psychology of sexual minorities, and provide recommendations for sex education and the development of sexual minorities. [Methods] This study used Python and Octopus to crawl the data of Weibo users and Zhihu users, TextMind to obtain the word frequence characteristics of emotional words, and machine learning methods to obtain life satisfaction indicators, and compared the difference between the word frequency characteristics and life satisfaction indicators of the coming-out group and the non-coming-out group. [Results] The proportion of negative emotion words (t ＝ -3.043, p ＜ 0.01) and sad words (t ＝ -2.211, p ＜ 0.05) in the group of non-coming-out group was significantly higher than that of the coming-out group. The life satisfaction of the people who did not come out was significantly lower than that of the people who came out (t ＝ 5.078, p ＜ 0.001). [Limitations] The non-coming-out group in this study was insufficiently sampled, and the subjects were not screened by age, selected variables were few and horizontal research, which made the research not comprehensive enough. [Conclusion] Coming out can improve the life satisfaction of sexual minorities and promote the mental health of them. "
Peer Review Status:Awaiting Review
Hits
Hits
Downloads
Comment