UCI Machine Learning Repository: Facebook Live Sellers in Thailand Data Set

Center for Machine Learning and Intelligent Systems

About Citation Policy Donate a Data Set Contact

View ALL Data Sets

Facebook Live Sellers in Thailand Data Set
Download: Data Folder, Data Set Description

Abstract: Facebook pages of 10 Thai fashion and cosmetics retail sellers. Posts of a different nature (video, photos, statuses, and links). Engagement metrics consist of comments, shares, and reactions.

Data Set Characteristics:	Multivariate	Number of Instances:	7051	Area:	Business
Attribute Characteristics:	Integer	Number of Attributes:	12	Date Donated	2019-04-22
Associated Tasks:	Clustering	Missing Values?	N/A	Number of Web Hits:	26619

Source:

Nassim Dehouche, Mahidol University International College, nassim.deh '@' mahidol.edu

Data Set Information:

The variability of consumer engagement is analysed through a Principal Component Analysis, highlighting the changes induced by the use of Facebook Live. The seasonal component is analysed through a study of the averages of the different engagement metrics for different time-frames (hourly, daily and monthly). Finally, we identify statistical outlier posts, that are qualitatively analyzed further, in terms of their selling approach and activities.

Attribute Information:

status_id
status_type
status_published
num_reactions
num_comments
num_shares
num_likes
num_loves
num_wows
num_hahas
num_sads
num_angrys

Relevant Papers:

Nassim Dehouche and Apiradee Wongkitrungrueng. Facebook Live as a Direct Selling Channel, 2018, Proceedings of ANZMAC 2018: The 20th Conference of the Australian and New Zealand Marketing Academy. Adelaide (Australia), 3-5 December 2018.

Citation Request:

Supported By:

In Collaboration With:

About || Citation Policy || Donation Policy || Contact || CML