Due to the absence of a dataset related to parenting styles at present, to explore the relationship between students' discourses and the parenting styles they experienced, we constructed a new parenting style dataset. We constructed this dataset via Weibo, the largest social media platform in China. To recruit participants, we posted announcements in the “University Student Questionnaire Completion” topic on Weibo. This topic, which gathers over 127,000 university students across the country, is the largest community for questionnaire completion on the platform.

Participants were asked to fill out a questionnaire that included their parenting style, Weibo ID (for collecting their public microblog data later), age, gender, payment account details, and real name. The payment account and real name were collected solely for the purpose of disbursing participant fees. Each participant who completed the questionnaire carefully received a compensation of 5 yuan. We used Python code to collect their open microblog data to construct a parenting style dataset.

To ensure data reliability and prevent individuals from completing the questionnaire multiple times using different accounts, we restricted submissions to one per IP address.

For the parenting style assessment, we used the short-form Chinese version of the EMBU (s-EMBU-C) (11). This 21-item questionnaire is widely applied in China and is well-suited for Chinese participants. Specifically, this questionnaire exhibits high reliability and validity, demonstrating a high degree of dependability. Its developer administered the questionnaire to 700 Chinese college students. The test - retest reliability of this questionnaire, measured after 10 weeks, ranges from 0.70 to 0.81. In terms of validity, this questionnaire has a significant correlation with the corresponding dimensions of the Chinese version of EMBU, with the correlation coefficients all above 0.8. The questionnaire evaluates three parenting dimensions: Rejection (six items), Emotional Warmth (seven items), and Overprotection (eight items). Responses were rated on a four-point Likert scale, ranging from “never occurs” to “always occurs.” Scores for each dimension were calculated as the average of the respective items.

To protect participant privacy, we implemented several measures. First, participants' payment account details and real names were permanently deleted after fee disbursement. Second, public Weibo data was collected using participants' Weibo IDs, ensuring that no personal information was exposed. Additionally, participants were fully informed before participation that their public Weibo data would be used for scientific research purposes.

We received a total of 3,183 questionnaires over the period of a month. Approximately one-third of the users did not supply their microblog usernames and were removed because we could not confirm their authenticity. Among the remaining users, a user was regarded as a valid student user if he/she satisfied the following conditions: (1) He/she answered the polygraph question correctly. We added a simple polygraph question: “For this question, please choose ‘occasionally occurs’ for your father and ‘always occurs’ for your mother.” (2) He/she had between 5 and 5,000 followers. Too few followers meant that he/she was not active enough on microblog and too many followers meant that he/she may be an institution or a public figure. (3) He/she had made more than 10 original posts in the past year. Too few original posts indicated low activity on the microblog. The data collection process received approval from the local ethics committee, reference number: 202302220019. After filtering, there were 575 valid students.

This dataset contains 575 microblog student users, including 281 males and 294 females. Each student was assigned three scores (s_r, s_e, and s_o) for the dimensions of Rejection, Emotional Warmth, and Overprotection. The age distribution ranged from 14 to 51 years, with an average age of 24.0 years and a standard deviation of 5.8 years. We wrote a Python program to collect all the open posts of these students dated from November 1, 2019, to October 31, 2022. Finally, we got 111,258 open posts from 575 students. Each student on average has 193.5 posts. The maximum and minimum numbers of posts made by a student were 1987 and 10, respectively. To develop the parenting style assessment method, we divided the 575 students into a training set of 475 students, a validation set of 50 students, and a test set of 50 students.

Figure 2 shows the distribution of parenting scores in the three dimensions. The average scores of the 575 students in the dimensions Rejection, Emotion warmth, and Overprotection were 1.59, 3.04, and 2.21, respectively.

Peng et al. (6) argued that parenting styles can be categorized into three types—positive, mixed, and negative—using Latent Profile Analysis (LPA). Following this approach, we classified the 575 students into these three types based on their scores in the dimensions of Rejection (s_r), Emotional warmth (s_e), and Overprotection (s_o):

Positive-parenting-style-type students. Students have higher scores in the dimension Emotional warmth and lower scores in the Rejection and Overprotection, i.e., (s_e > s_r + 1)&(s_e > s_o + 1).

There are 379 (66.4%), 162 (28.4%), and 16 (2.8%) students who grew up under positive, mixed, and negative parenting style types. Moreover, there are 14 (2.5%) students whose parenting style scores did not satisfy the above three types, e.g., (s_r + 1 < s_e)&(s_e < s_o). Those students were not considered in the following analysis. The statistical results are broadly in line with the statistical finding reported by Peng et al. (6) that the proportions of positive, mixed, and negative parenting style types are 69.1%, 22.3%, and 8.6%, respectively. Figure 3 shows the average scores of the three parenting style types in the dimensions Rejection, Emotional warmth, and Overprotection, respectively.

We analyzed the difference between the three parenting style types from the perspectives of linguistic expressions and emotional expressions in discourses.

Table 1 lists the topic-related word frequencies used by the three types of students on microblogs. The word frequencies were calculated using the Simplified Chinese Linguistic Inquiry Word Count, TextMind (15). The corpus contains 72,748 open posts from positive-parenting-style-type students, 34,326 from mixed-parenting-style-type students, and 2,366 from negative-parenting-style-type students. There are 11 topics, i.e., “social,” “family,” “friend,” “health,” “work,” “leisure,” “money,” “religion,” “death,” “psychology,” and “love.” The differences between the maximum and secondary maximum word frequencies are significant (p < 0.01) for all topics. We found that compared with the other types of students, positive-parenting-style-type students were more prone to use words related to topics like “social,” “family,” “friend,” “work,” “leisure,” “money,” and “psychology.” Mixed-parenting-style-type students talked more about “religion.” Negative-parenting-style-type students used more words related to “health,” “death,” and “love.” Besides, “Social,” “work,” and “leisure” are the most frequently discussed topics.

From the perspective of emotional expression (Table 2), we observe that students under the positive and mixed parenting style types wrote more posts with positive emotions (i.e., “happy,” “like,” and “surprise”) whereas negative-parenting-style-type students tended to express more negative emotions (i.e., “sad,” “fear,” and “hate”) in their posts. We used the Chinese Affect Lexicon (16) including 27,466 words from seven emotional categories, i.e., “happy” (1,967 words), “like” (11,108 words), “surprised” (228 words), “angry” (388 words), “sad” (2,314 words), “fear” (1,179 words), and “hate” (10,282 words). Table 2 lists the mean proportions of emotional words used by students under the three types of parenting styles. We conducted a student's t-test and verified that the differences between different types of student were significant (p < 0.01) in the emotional categories “happy,” “like,” and “sad.” As the significant predictor of suicidal ideation, more attention should be paid to the negative parenting style type (17, 18).

From Table 2, we further observe that under the negative parenting style type, there is a significant difference (p < 0.01) in the emotional expression between male and female students. Female students tend to express more negative emotions (i.e., “sad,” “fear,” and “hate”) than male students. Under the negative parenting style type, the female students' most common negative emotion is hate. Moreover, we conducted a t-test to investigate the effect of gender on negative emotional expressions. As shown in Table 3, under the negative parenting style type, the effect is more significant than that under a positive or mixed parenting style type.

Overall, the differences in discourse among microblog university student users with different parenting styles indicate that it is feasible to assess parenting styles based on students' language patterns. These variations in students' expressions provide valuable insights, allowing us to focus on specific aspects when evaluating their parenting styles. In the next chapter, we incorporate these discourse differences into the construction of our assessment method to improve its accuracy and reliability.

To obtain a better performance in parenting style assessment, we designed a tailor-made module (Figure 5), injecting the found correlations into the assessment method. These correlations are that students who grew up in different parenting styles have different tendencies in linguistic and emotional expressions. This insight led our method to focus on words related to positive, mixed, and negative parenting styles, allowing our method to achieve more accurate parenting style predictions.

According to the respective tendencies of the three types of students, we created three topic word sets (T_p, T_m, T_n) and three emotional word sets (E_p, E_m, E_n), respectively. For instance, T_n contains 497 topic words that negative-parenting-style students tend to use, that is, words related to topics like “health,” “death,” and “love.” The statistical information of word sets T_p, T_m, T_n, E_p, E_m, E_n is shown in Table 4. All words are from the Simplified Chinese Linguistic Inquiry Word Count (15) and the Chinese Affect Lexicon (16).

Let Tn′∈ℝ497×300,En′∈ℝ13775×300 be the word embedding sets of all words in T_n and E_n. All the word embeddings were calculated by Sentence BERT (14). Let Tn″∈ℝ1×300,En″∈ℝ1×300 be the average of all word embeddings in Tn′ and En′, respectively. Tn″ and En″ can be seen as the representations of topic and emotional words that negative-parenting-style students tend to use. We used the same approach to generate Tp″∈ℝ1×300, Ep″∈ℝ1×300, Tm″∈ℝ1×300, and Em″∈ℝ1×300.

To inject the found correlations into the assessment method, we concatenated the discourse information H′ and the six representations, generated the correlation-aware discourse representation C: (4)C=H′||Tp″||Ep″||Tm″||Em″||Tn″||En″∈ℝ1×2100, where || is the concatenate operation. C contains not only key discourse information (H′) but also the correlation information between discourse and parenting style (e.g., Tn″), which allows our method to more accurately evaluate the parenting style of the student's parents.

Finally, given the correlation-aware discourse representation C, the assessment method needs to deeply understand the student's discourse information and refer to the correlation information between the discourse and the parenting style to give the final parenting style assessment. Two fully-connected layers were utilized in this step: (5)              U=Tanh(C×W2+b2)∈ℝ1×128,{sr,se,so}=Tanh(R×W3+b3), where U is the intermediate result, W2∈ℝ2100×128, W3∈ℝ128×3, b2∈ℝ1×128, and b3∈ℝ1×3 are learnable parameters. s_r, s_e, s_o are the predicted scores of the parenting style of the parents of the student in the dimensions Rejection, Emotional Warmth, and Overprotection. Higher scores indicate higher levels. In this step, we tried single-layer, two-layer, and three-layer fully-connected layers respectively, and found that the assessment performance of two-layer was the best.

In theoretical significance, our research holds great theoretical importance in the field of parenting style assessment. By leveraging social-media-based natural language processing techniques, it challenges the traditional research paradigm that mainly relies on questionnaires and interviews. This novel approach provides a more naturalistic and large-scale data source for studying parenting styles. It enriches the theoretical framework by enabling a more in-depth exploration of the relationship between parents' implicit parenting behaviors (reflected in students' discourses on social media) and the established parenting style dimensions of Rejection, Emotional Warmth, and Overprotection.

In practical significance, the proposed parenting style assessment method has far-reaching implications. For educational institutions, especially universities, it offers a cost-effective and scalable solution to identify students who may have experienced negative parenting styles. This early identification can help in providing timely psychological interventions, reducing the likelihood of students developing mental health issues such as anxiety and depression. In the context of family education, parents can use this method to gain insights into their own parenting styles, facilitating self-reflection and potential adjustments to create a more nurturing environment for their children.

In terms of methodological innovation, we introduce a new way of assessing parenting styles. Prior to this study, most research on parenting style assessment was based on self-reported questionnaires or face-to-face interviews, which are often subject to respondent bias and limited sample sizes. Our method, on the other hand, mines students' social media posts, providing a more objective and real-time view of their perceived parenting experiences. This not only overcomes the limitations of traditional methods but also uncovers new patterns in how parenting styles are manifested in natural language.

In addition, we summarize some insights on model design. Through the ablation study and comparison with baseline methods, we have discovered the importance of certain layers in our model, such as the attention layer and correlation injection layer. The attention layer can effectively focus on the relevant parts of students' discourses related to parenting styles, while the correlation injection layer helps in establishing key correlations between the text data and parenting style dimensions. These findings contribute new knowledge on how to better extract features from text for the task of parenting style assessment.

For future research, our error analysis indicates several directions for future research. Given that the number of posts and the presence of quotations affect the assessment accuracy, future studies could focus on developing more advanced sampling techniques to deal with limited data and more sophisticated text-filtering algorithms to exclude non-relevant information. Additionally, exploring how to integrate other types of data sources (such as multimedia content on social media) with text data may further improve the assessment performance.

For practical applications, schools and universities can incorporate this assessment method into their routine mental health screening programs. Teachers and counselors can use the assessment results to design personalized support plans for students who have experienced negative parenting styles. In the family context, parents can be educated about the importance of positive parenting styles based on the assessment results, and provided with resources and guidance on how to improve their parenting skills.

Our research advances the understanding of how parenting styles are reflected in the linguistic and emotional expressions of students on microblogs. The novel contributions of our work are shown in following:

Exploration of parenting styles and student discourse: few of the previous references have examined the correlations between students' discourses on microblog and parents' parenting styles. In this study, we found that positive, mixed, and negative parenting styles affect linguistic expression and emotional expression in microblog discourse. Under the negative parenting style, the effect of sex on negative expressions is greater. These findings contribute to the studies of parenting style, sex differences, and emotional analysis.

Our research also carries significant practical implications, particularly in the development of tool for assessing parenting styles through microblogs. This tool offers:

Support for healthcare institutions: we proposed the first assisting tool that could be used by healthcare institutions to identify students' parenting styles. It facilitates the identification of suicide risk factors among microblog student users, and enables timely interventions to prevent suicides, which enhances human wellbeing and saves lives.