Big consumer data promises to be a game changer in applied and empirical marketing research. However, investigations of how big data helps inform consumers’ psychological aspects have, thus far, only received scant attention. Psychographics has been shown to be a valuable market segmentation path in understanding consumer preferences. Although in the context of e-commerce, as a component of psychographic segmentation, personality has been proven to be effective for prediction of e-commerce user preferences, it still remains unclear whether psychographic segmentation is practically influential in understanding user preferences across different product categories. To the best of our knowledge, we provide the first quantitative demonstration of the promising effect and relative importance of psychographic segmentation in predicting users’ online purchasing preferences across different product categories in e-commerce by using a data-driven approach. We first construct two online psychographic lexicons that include the Big Five Factor (BFF) personality traits and Schwartz Value Survey (SVS) using natural language processing (NLP) methods that are based on behavior measurements of users’ word use. We then incorporate the lexicons in a deep neural network (DNN)-based recommender system to predict users’ online purchasing preferences considering the new progress in segmentation-based user preference prediction methods. Overall, segmenting consumers into heterogeneous groups surprisingly does not demonstrate a significant improvement in understanding consumer preferences. Psychographic variables (both BFF and SVS) significantly improve the explanatory power of e-consumer preferences, whereas the improvement in prediction power is not significant. The SVS tends to outperform BFF segmentation, except for some product categories. Additionally, the DNN significantly outperforms previous methods. An e-commerce-oriented SVS measurement and segmentation approach that integrates both BFF and the SVS is recommended. The strong empirical evidence provides both practical guidance for e-commerce product development, marketing and recommendations, and a methodological reference for big data-driven marketing research.

Online lifestyles have been shown to reflect and affect consumers’ preferences across a wide range of online scenarios. In the context of e-commerce, it still remains unclear whether online lifestyles are practically influential in predicting consumers’ purchasing preferences across different product categories, especially considering its potential influence over the widely used personality traits. In this study, we provide the first, to the best of our knowledge, quantitative demonstration of online lifestyles in predicting consumers’ online purchasing preferences in e-commerce by using a data-driven approach. We first construct an online lifestyles lexicon including seven distinct dimensions using text mining approaches based on consumers’ language use behaviors. We then incorporate the lexicon in a typical e-commerce recommender system to predict consumers’ purchasing preferences. Experimental results on Amazon Review Dataset show that online lifestyles and all its subdimensions significantly improve preference predicting performance and outperform the widely used Big Five personality traits as a whole. In addition, product types significantly moderate the influence of online lifestyle on consumer preference. The strong empirical evidence indicates that the big e-commerce consumer data facilitates more specialized market psychographic segmentation, which advances data-driven marketing decision-making.

Online mental health service (OMHS) has been named as the best psychological assistance measure during the COVID-19 pandemic. An interpretable, accurate, and early prediction for the demand of OMHS is crucial to local governments and organizations which need to allocate and make the decision in mental health resources. The present study aimed to investigate the influence of the COVID-19 pandemic on the online psychological help-seeking (OPHS) behavior in the OMHS, then propose a machine learning model to predict and interpret the OPHS number in advance. The data was crawled from two Chinese OMHS platforms. Linguistic inquiry and word count (LIWC), neural embedding-based topic modeling, and time series analysis were utilized to build time series feature sets with lagging one, three, seven, and 14 days. Correlation analysis was used to examine the impact of COVID-19 on OPHS behaviors across different OMHS platforms. Machine learning algorithms and Shapley additive explanation (SHAP) were used to build the prediction. The result showed that the massive growth of OPHS behavior during the COVID-19 pandemic was a common phenomenon. The predictive model based on random forest (RF) and feature sets containing temporal features of the OPHS number, mental health topics, LIWC, and COVID-19 cases achieved the best performance. Temporal features of the OPHS number showed the biggest positive and negative predictive power. The topic features had incremental effects on performance of the prediction across different lag days and were more suitable for OPHS prediction compared to the LIWC features. The interpretable model showed that the increase in the OPHS behaviors was impacted by the cumulative confirmed cases and cumulative deaths, while it was not sensitive in the new confirmed cases or new deaths. The present study was the first to predict the demand for OMHS using machine learning during the COVID-19 pandemic. This study suggests an interpretable machine learning method that can facilitate quick, early, and interpretable prediction of the OPHS behavior and to support the operational decision-making; it also demonstrated the power of utilizing the OMHS platforms as an always-on data source to obtain a high-resolution timeline and real-time prediction of the psychological response of the online public.

Online mental health service (OMHS) platforms have contributed significantly to the public’s mental health during the COVID-19 pandemic in China. However, it remains unclear why the public used OMHS platforms for psychological help-seeking (PHS) behavior and how PHS behavior varied across different stages of the COVID-19 pandemic. Based on the ecological PHS behavior data from two OMHS platforms, we extracted population, psychological problems, and influential factors of PHS behavior by text mining and time series analysis methods. Seven top-ranked psychological problems (i.e., depression and anxiety, lack of interest, suicidal tendencies, social phobia, feelings of being worried and afraid, suffering, anger) and seven influential factors (i.e., interpersonal relationships, love, family, work, psychotherapy, personal characteristics, marriage) were found. The online PHS behaviors related to different psychological problems and influential factors remained a growing trend before 2020 and have been increasing significantly due to the COVID-19 outbreak. Four main stages were found during the pandemic according to the changes in the online PHS population: sharp growth, significant decline, slight rebound, and slow decline. This study identified large-scale, spontaneous PHS behaviors among the online public during the COVID-19 pandemic and the various psychological problems and influential factors that varied across different stages of the pandemic, suggesting that the government and health practitioners should adopt effective policies and strategies to prevent and intervene in mental health problems for the online public.

Despite the great attention paid to Internet literacy research, little has been done to overcome the problems stemming from the heterogeneity of Internet literacy nomenclature and the use of non-standardized measurement tools, especially for adolescents in developing countries. Considering junior students are the high-risk groups of Internet addiction and have wide access to the Internet, the aim of this study is to develop a new scale to assess Chinese junior students’ Internet literacy (JIL). In the psychometric study (n = 1099 junior students), an 18-item scale was developed using the exploratory and confirmatory factor analyses, which includes five subscales: knowledge and skills for the Internet (KSI), Internet self-management (ISM), awareness and cognition of Internet (ACI), Internet interactions (II), and autonomous learning on the Internet (ALI). Evidence of internal reliability, test-retest reliability, and construct validity provided good psychometric support for the measure. Criterion-related validity of the measures was demonstrated by examining its anticipated theoretical relations to two hypotheses: (1) High JIL level alleviates the adverse effects of an individual’s Internet addiction degree, while pathological use for interacting with others on the Internet exacerbates the adverse effects; (2) an individual’s degree of Internet use self-efficacy is positively associated with JIL level. It is envisaged that the JIL Scale will help facilitate unified research in the field.