The Method of How to Predict Weibo Users’ Recovery Experience on the Weekend Based on Weibo Big Data

Peng Wang,Runsheng Pan,Jun Wang,Weixuan Meng,Denghao Zhang,Yu Sun,Xiaoyue Li,Xiangping Zhan

doi:10.1109/access.2020.3032850

Peng Wang, Runsheng Pan + Show 6 more

Open Access

https://doi.org/10.1109/access.2020.3032850

Copy DOI

Abstract

The prevailing “996” overtime phenomenon in China has raised extensive consideration and discussion towards the topic of work-life balance. Following this trend, this study focused on the topic of work recovery experience. Based on Lens Model, we aimed to construct prediction models of weekend recovery experience with individuals' social media footprints, which include their social media posts, behavioral information, and demographic information. We acquired Weibo data and Recovery Experience Questionnaire results from 493 participants and extracted Weibo data features for model training through two methods. As a result, two types of model were constructed: regression models which applied Ridge Regression, LASSO Regression, and Elastic Net; classification models which applied Gradient Boosting Decision Tree, Logistic Regression and Support Vector Machine. For the results of regression models, Pearson correlation coefficients between predicted values and self-reported scores ranged from 0.40 to 0.84; for classification models, F1-score ranged from 0.49 to 0.78. The results showed that individuals' recovery experience on weekends could be predicted by their social media footprints. What is more, the methodology proposed in this study could help organizations to evaluate large groups of employees' work recovery in real-time, which will have further implications for both theoretical and practical purposes.

Highlights

In contemporary Chinese society, with the prevalence of the “996” overtime culture, working overtime has become a primary daily stressor for many people
In the view of the importance of recovery experience in maintaining physical and mental health, improving individuals’ well-being, job performance and organizational effectiveness [4,5,6, 37], and the limitations of traditional measurement methods used in previous studies of recovery experience, this study proposed a new approach to predict Weibo user’s recovery experience on the weekend by applying Weibo text and behavior data with text mining technology
Regression Prediction Model After using the principal component analysis (PCA) method to reduce the dimension of the features, we further evaluated the correlations between the number of extracted principal components and the performance of models

Summary

Introduction

In contemporary Chinese society, with the prevalence of the “996” overtime culture, working overtime has become a primary daily stressor for many people. With “Work 996, Sick ICU” once became a hot topic on Weibo [2], employees’ dissatisfaction and resistance towards the “996” work system began to erupt, which reflected that job stress and burnout has become a serious and common problem in today’s society If these negative consequences of lacking rest are not recovered on time within the appropriate time cycle, they could further affect the physical and mental health of employees and their performance in organizations. Previous research has shown that the level of recovery from work over weekends improves employees’ Monday’s work status and leads to more positive emotional experiences in the following new week [6]. It is essential for employees and organizations to assess recovery from work during weekends reasonably

Objectives

Methods

Results

Discussion

Conclusion