Data in Brief

The research article "Realtime Online Courses Mutated amid the COVID-19 Pandemic: Empirical Study in Hospitality Program" aims to explore the education evolution amid the pandemic [1] . Data were collected by recruiting 956 respondents; 926 responses were adopted after the valid screening through a cooperative survey company. A random sampling of targeted groups was required when outsourcing the data collection to the survey company Wenjuanxing, a platform with a majority population database providing functions equivalent to Amazon Mechanical Turk [2] . We asked the company to deliver the designed questionnaire to teachers and students in hospitality programs. The reliability and validity of all constructs showed that the questionnaire is proper for measurement [3] . Data analysis applied the structural equation model with Mplus to examine the CFA model and research hypothesis. Structural equation modeling was applied to conduct the hypotheses test and model ﬁtness through the statistical tool Mplus. Results imply that the data is suitable for conducting replication studies.


a b s t r a c t
The research article "Realtime Online Courses Mutated amid the COVID-19 Pandemic: Empirical Study in Hospitality Program" aims to explore the education evolution amid the pandemic [1] .Data were collected by recruiting 956 respondents; 926 responses were adopted after the valid screening through a cooperative survey company.A random sampling of targeted groups was required when outsourcing the data collection to the survey company Wenjuanxing, a platform with a majority population database providing functions equivalent to Amazon Mechanical Turk [2] .We asked the company to deliver the designed questionnaire to teachers and students in hospitality programs.The reliability and validity of all constructs showed that the questionnaire is proper for measurement [3] .Data  Data were collected by recruiting 956 respondents; 926 responses were adopted after the valid screening through a cooperative survey company.A random sampling of targeted groups was required when outsourcing the data collection to the survey company Wenjuanxing, a platform with a majority population database providing functions equivalent to Amazon Mechanical Turk [2] .We asked the company to deliver the designed questionnaire to teachers and students in hospitality programs through a random sampling approach in their population database.The reliability and validity of all constructs showed that the questionnaire is proper for measurement [4]

Value of the Data
• The data is useful because it is applied to the research model we have done and could also extend the model with more constructs to conduct the competitive statistical models.The measurement scales of learning outcomes could apply different analysis methods because the scales were developed into two various forms.One form is Bloom's Taxonomy of the Cognitive Domain, with six levels of learning outcome in a question; the other question item measures six levels individually.We conducted SEM to test the model using the later form.
One might use regression analysis to test the cause-effect between two constructs.For example, a regression analysis from the cause construct "social media functionality" to the effect construct "learning outcome" applied the former form.• Professors can also use the data to illustrate a course in statistical exploitation of survey data that focuses on structural equation modeling.The scientific and pedagogical orientations can be highlighted in teaching and learning.The varying responses could tell the various learning effects.
• The data could be applied to conduct replicated studies with competitive statistical models to compare the goodness-of-fit for observing the insights of education mutation amid the COVID-19 pandemic.In addition, the data can also conduct cross-regions in the greater China regions, including the Chinese Mainland, Hong Kong, and Macau.The cross-region studies could statistically extend the research generalizability if the data could be collected more out of the greater China regions.As we argued above, further studies could be conducted to compare learning outcomes with various pandemic control policies while obtaining different datasets for other countries.

Data Description
The raw data is measured from the questionnaire designed by the research team based on the literature review of the research constructs [5] .The questionnaire items are in Table 1 , showing the variables' measurement scales.Q1 ∼Q3 variables are the second level of social media construct, which is the channel for conducting real-time online courses amid the COVID-19 pandemic.Q4 and Q5, the second level of information construct, represent the teaching and learning information that transmits in the education system.Q6 and Q7 are the same learning outcome, where Q6 questions are measured individually to apply to the structural equation modeling (SEM) technique in the related research article [1] .Q7 is a question that could be used for the other analysis technique, such as regression analysis.Q8 ∼Q10 variables measure the structural differentiation construct, including the second-level constructs of individual technique and instruction rule dimensions.The descriptive analysis of questionnaire items is presented in Table 1 for reference.The rest of the questions, Q11 ∼Q16, are the demographical measure scales with descriptive analysis results, as indicated in Table 2 .The questionnaire and raw data are provided on Mendeley data at https://doi.org/10.17632/6gjyr6vm9g.1 .

Experimental Design, Materials and Methods
Table 3 shows the experimental design from the model construction to the analysis method.The research design began with the model and hypotheses construction based on the information theory intervening by the social media and structural differentiation constructs.Then a questionnaire was developed with measurement scales of variables referred to and supported by the literature.The raw data were generated through a survey that measured participants' cognitions of the model constructs.The researchers collected a sample size of 957 participants, analysis applied the structural equation model with Mplus to examine the CFA model and research hypothesis.Structural equation modeling was applied to conduct the hypotheses test and model fitness through the statistical tool Mplus.Results imply that the data is suitable for conducting replication studies.© 2022 The Author(s).Published by Elsevier Inc.This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )

Table 1
The questionnaire and variable descriptive analysis.

Table 2
The descriptive demographic analysis.

Table 3
The experimental design process.