Subjects: Psychology >> Applied Psychology Subjects: Computer Science >> Computer Application Technology submitted time 2024-04-09
Abstract： In recent years, the Linguistic Inquiry and Word Count (LIWC) tool has garnered increasing attention, offering the promise of objective, automated, and transparent psychological text analysis. This resurgence has reignited enthusiasm among psychologists for language analysis research. The recent revision of the LIWC-22 dictionary has introduced numerous variables aimed at assessing various socio-psychological structures, thus expanding the application potential of the LIWC tool. To further promote the cultural adaptation of the LIWC tool, we have revised and validated the Simplified Chinese Linguistic Inquiry and Word Count Dictionary 2024 (SCLIWC2024) to better align with the features of LIWC-22. In Study One, building upon the SCLIWC dictionary, we revised SCLIWC2024 by comparing it with the LIWC-22 and CLIWC2015 dictionaries. In Study Two, we conducted two experiments to validate the efficacy of SCLIWC2024 in detecting different psychological semantics in online texts, addressing crucial questions regarding how to more effectively utilize SCLIWC2024 for detecting the psychological semantics of short texts on social networking platforms.
Peer Review Status:
Awaiting Review
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 >> Social Psychology submitted time 2023-03-28 Cooperative journals: 《心理科学进展》
Abstract： Modeling psychological indexes (i.e., psych-modeling) is an emerging method that uses machine learning algorithms to identify psychological indexes based on big data. This paper reviews the feasibility of psych-modeling methods based on social media data in the field of psychometrics. Frequently used data types and machine learning algorithms are introduced. Then, we summarize psych-modeling's application to various scenarios together with its strengths and weaknesses. Compared with traditional self-reporting methods, psych-modeling has some advantages, including better performance in retrospective studies, greater ecological validity, and greater time-efficiency. However, psych-modeling has several limitations. For example, researchers need to spend extra time and effort to learn this new method and bear the inevitable cost of hardware. In future studies, researchers could investigate further how user's behavior on social media relates to psychological indexes. We also expect psych-modeling will be used in future psychological studies. By combining psychometrics and machine learning, we believe psych-modeling could make great contributions to psychology research and practice in the future.
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] This study is based on the Tianya community and explores the differences in parents' life satisfaction and emotional state when children at different educational stages. [Methods] The word frequency distribution of parents whose children are in preschool, primary school and junior middle school is calculated by using the Emotion Dictionary of Dalian Institute of Technology, and the life satisfaction of the parents is predicted based on the word frequency. We then compare the differences in parents' life satisfaction and emotional state between groups. [Results] For life satisfaction, junior high school parents were significantly lower than preschool parents and primary school parents. The result indicated that in terms of happy emotional words, the word frequency of pre-school parents was higher than that of primary and junior middle school parents. While in terms of reassuring words and praising words, the word frequency of junior middle school parents was higher than that of pre-school parents. In the category of believing words, parents whose children are in junior high school had the highest word frequency. Pre-school parents had the highest word frequency, and primary school parents had the second higher word frequency in terms of affectionate words. With regard to the missing words and panic words, junior high school parents’ word frequency was significantly higher than primary school parents, with more panic words being expressed by junior high school parents than preschool parents as well. [Limitations] This study collected the data based on the Tianya community, in which this study might ignore the possibility that some parents may still record their lives in the same post while their children’s educational stages have changed. Future research can focus more on possible influencing factors (e.g., high school parents, different roles of parents, longitudinal study) in the relationship between children’s educational stages and parents’ life satisfaction. [Conclusions] In terms of life satisfaction, junior high school parents were significantly lower than preschool and primary school parents. In terms of emotional expression, there are variations between parents whose children are at different educational stages on various emotional words, including happy, reassuring, praising, believing, affectionate, missing, panic words. " " "
Peer Review Status:Awaiting Review
Subjects: Psychology >> Applied Psychology submitted time 2022-03-06
Abstract：
[Objective] This study aims to explore the relationship between staying up late, different development levels of cities and life satisfaction with the method of big data in Weibo, so as to increase the understanding of life satisfaction of contemporary people. [Method]The users in Weibo were divided into those who stayed up late and didn't stay up late in first-tier cities and other cities according to user’s information of blog posting. In addition, the statistical difference in life satisfaction between people who stayed up late and didn't stay up late in different areas was compared. [Results] (1) The life satisfaction of Weibo users who stayed up late was significantly higher than that of non-staying up late group (t = 11.768, p < 0.05); (2) Life satisfaction of Weibo users in first-tier cities was significantly lower than that of users in other cities (t =-4.135, p < 0.05); (3) The life satisfaction of staying up late in first-tier cities was significantly lower than that of staying up late in other cities (p < 0.05), and there was no statistically significant difference between non-staying up late in first-tier cities and non-staying up late in other cities (p > 0.05); (4) The life satisfaction of staying up late in first-tier cities was significantly higher than that of non-staying up late in first-tier cities (p < 0.05), and that of staying up late in other cities was significantly higher than that of non-staying up late (p < 0.05). [Conclusion] The staying up late behavior of contemporary Weibo users will improve their life satisfaction to a certain extent. However, the life satisfaction of Weibo users in first-tier cities is lower than that of Weibo users in other cities. "
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
Subjects: Psychology >> Applied Psychology submitted time 2020-11-05
Abstract： Modeling psychological indexes (i.e., psych-modeling) is an emerging method that uses machine learning algorithms to identify psychological indexes based on big data. This paper reviews the feasibility of psych-modeling methods based on social media data in the field of psychometrics. Frequently used data types and machine learning algorithms are introduced. Then, we summarize psych-modeling’s application to various scenarios together with its strengths and weaknesses. Compared with traditional self-reporting methods, psych-modeling has some advantages, including better performance in retrospective studies, greater ecological validity, and greater time-efficiency. However, psych-modeling has several limitations. For example, researchers need to spend extra time and effort to learn this new method and bear the inevitable cost of hardware. In future studies, researchers could investigate further how user’s behavior on social media relates to psychological indexes. We also expect psych-modeling will be used in future psychological studies. By combining psychometrics and machine learning, we believe psych-modeling could make great contributions to psychology research and practice in the future.
Peer Review Status:Awaiting Review
Subjects: Psychology >> Applied Psychology submitted time 2020-02-05
Abstract： [Objective] To explore the influence of public health emergencies on the psychological state of the public, and understand its changing characteristics and rules. [Methods] We acquire active Weibo users from 2020/1/13 to 2020/2/26 at first, and extract features from these users’ data, including word frequency, negative (anxiety, depression and force), positive (life satisfaction and oxford happiness) and social attitudes (social risk judgment and anger) index. We then compare the differences of psychological characteristics between 2020/1/13-2020/1/19 and 2020/1/20-2020/1/26. [Results] The result indicates that the frequency of negative emotional words (t=-18.533, p < 0.05) and anxious words were increased (t=-17.433, p < 0.05), family words (t=7.907, p < 0.05) and friend words decreased (t=6.897, p < 0.05) after 20-th. Meanwhile, anxiety (t=-35.962, p < 0.05), depression (t=-10.717, p < 0.05) and obsessiveness (t=-24.755, p < 0.05) were increased. Oxford happiness (t=3.120, p < 0.05) and life satisfaction (t=5.500, p < 0.05) were decreased. The levels of social risk judgment (t=-8.832, p < 0.05) and anger (t=-11.415, p < 0.05) were increased. [Limitations] The weekly measurement of the data is considered as a relatively large scale, which has a certain influence on reflecting the trend of social mentality timely. [Conclusions] After the official confirmation and attention to the incident, the overall state of mind of the society showed an increase in negative emotions such as anxiety and anger, as well as a decrease in well-being and an increase in sensitivity to social risks.
Peer Review Status:Awaiting Review
Hits
Hits
Downloads
Comment