#Coronavirus On TikTok by Kaggle | Finance and Economics

About this Dataset

#Coronavirus On TikTok

#Coronavirus on TikTok:

Examining Factors Related to Reception of Content

About this dataset

This dataset explores various factors associated with the reception of COVID-19 related content on TikTok. It not only captures overall levels of user engagement such as likes, comments, and views but also explores source credibility including information from healthcare professionals, news sources, patients, and other outlets. It further dives into demographic factors such as gender and age range as well as content type like humor or provision of clinical instruction. Finally, it takes a look at elements such as description of risk factors & symptoms along with modes of transmission established by the posts in question and prevention that was discussed within them. Moreover, there is a discernment component that breaks down user perception - rating the posts for level of misinformation (moderate/high/low). All these measures combined provide insights into how users are engaging with COVID-19 related misinformation on TikTok

More Datasets

For more datasets, click here.

Featured Notebooks

🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset contains user engagement data and measures of source credibility related to COVID-19 misinformation on TikTok. It can be used to examine the factors associated with content reception, such as views, likes, comments, as well as factors relating to credibility, demographics and content type.

Using this dataset:

Explore the columns available in the dataset. There are a number of columns that measure user engagement (views, likes and comments) as well as source credibility (official source, healthcare professional etc.), demographic factors (gender, age group etc.), and content type (humor etc). Get familiar with all these columns so that you know what information is available for analysis.

Decide what kind of analysis you want to perform. You can use this data for exploratory or explanatory work - depending on your aims or research question. For example if you want to see how source credibility affects user engagement then you would need descriptive statistical techniques such as correlation tests or regression analyses etc., whereas if you just want to gain an overall understanding of patterns in this data then exploratory techniques such as cross tabulations may be more suitable.

Research Ideas

Developing a predictive model to identify which demographic and source characteristics are correlated with high user engagement for COVID-related posts on TikTok (e.g. views, likes, and comments).

Investigating the difference in user engagement for posts from healthcare professionals vs non-professional sources to compare how different types of content are received by users on TikTok.

Analyzing the sentiment of words related to masks and tests in order to gain insights into how content about this topic is perceived by users on TikTok (i.e., positive or negative sentiment)

Acknowledgements

If you use this dataset in your research, please credit the original authors.
Data Source

License

License: CC0 1.0 Universal (CC0 1.0) - Public Domain Dedication
No Copyright - You can copy, modify, distribute and perform the work, even for commercial purposes, all without asking permission. See Other Information.

Columns

File: tiktok_data_open.csv

Column name	Description
views	Number of views for the video. (Integer)
likes	Number of likes for the video. (Integer)
comments	Number of comments for the video. (Integer)
official_source	Whether the source of the video is an official source. (Boolean)
pub_hcp	Whether the source of the video is a healthcare professional. (Boolean)
pub_news	Whether the source of the video is a news source. (Boolean)
pub_patient	Whether the source of the video is a patient. (Boolean)
pub_other	Whether the source of the video is another source. (Boolean)
female	Whether the gender of the viewer is female. (Boolean)
gender_other	Whether the gender of the viewer is other. (Boolean)
age00	Whether the age of the viewer is 0-29. (Boolean)
age30	Whether the age of the viewer is 30-49. (Boolean)
age50	Whether the age of the viewer is 50+. (Boolean)
age_unk	Whether the age of the viewer is unknown. (Boolean)
topic_humor	Whether the video is humorous. (Boolean)
topic_ip	Whether the video provides information. (Boolean)
topic_clinical	Whether the video provides clinical instruction. (Boolean)
d_descriptionofriskfactors	Whether the video discusses risk factors. (Boolean)
d_descriptionofsymptoms	Whether the video discusses symptoms. (Boolean)
d_modesoftransmission	Whether the video discusses modes of transmission. (Boolean)
d_masks	Whether the video discusses masks. (Boolean)
d_demonstratewearingmask	Whether the video demonstrates wearing a mask. (Boolean)
d_eyeprotection	Whether the video discusses eye protection. (Boolean)
d_handhygiene	Whether the video discusses hand hygiene. (Boolean)
d_socialdistancing	Whether the video discusses social

Acknowledgements

If you use this dataset in your research, please credit the original authors.
If you use this dataset in your research, please credit .

Tables

Tiktok Data Open

@kaggle.thedevastator_user_engagement_with_covid_misinformation_on_tik.tiktok_data_open

35.91 KB
166 rows
46 columns


CREATE TABLE tiktok_data_open (
  "views" BIGINT,
  "likes" BIGINT,
  "comments" BIGINT,
  "official_source" BIGINT,
  "pub_hcp" BIGINT,
  "pub_news" BIGINT,
  "pub_patient" BIGINT,
  "pub_other" BIGINT,
  "female" BIGINT,
  "gender_other" BIGINT,
  "age00" BIGINT,
  "age30" BIGINT,
  "age50" BIGINT,
  "age_unk" BIGINT,
  "topic_humor" BIGINT,
  "topic_ip" BIGINT,
  "topic_clinical" BIGINT,
  "d_descriptionofriskfactors" BIGINT,
  "d_descriptionofsymptoms" BIGINT,
  "d_modesoftransmission" BIGINT,
  "d_masks" BIGINT,
  "d_demonstratewearingmask" BIGINT,
  "d_eyeprotection" BIGINT,
  "d_handhygiene" BIGINT,
  "d_socialdistancing" BIGINT,
  "d_testing" BIGINT,
  "d_preventiondiscussed" BIGINT,
  "d_quarantining" BIGINT,
  "d_commercialbias" BIGINT,
  "masksent_pos" BIGINT,
  "masksent_neg" BIGINT,
  "masksent_neu" BIGINT,
  "testsent_pos" BIGINT,
  "testsent_neg" BIGINT,
  "testsent_neu" BIGINT,
  "discern_moderate" BIGINT,
  "discern_high" BIGINT,
  "discern_low" BIGINT,
  "discern_mh" BIGINT,
  "p_understand_high" BIGINT,
  "p_action_high" BIGINT,
  "misinfo_high" BIGINT,
  "misinfo_mod" BIGINT,
  "misinfo_level" BIGINT,
  "misinfo_any" BIGINT,
  "behavior_change" BIGINT
);