Classification and Analysis of Personal and Commercial CBD Tweets

Jason S. Turner; Mehmed M. Kantardzic; Rachel Vickers-Smith

doi:10.1007/978-3-030-72805-2_10

Classification and Analysis of Personal and Commercial CBD Tweets

Jason S. Turner, Mehmed M. Kantardzic, Rachel Vickers-Smith

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This study analyzes the differences in terms regarding cannabidiol (CBD) expressed by commercial sellers and personal users on Twitter. It demonstrates that data from social networks can be used by public health and medical researchers to compare the medical conditions targeted by those selling loosely-regulated substances such as CBD against the medical conditions that patients themselves are commonly treating with CBD. We collected 567,850 tweets by searching Twitter with the Tweepy Python package using the terms CBD and cannabidiol, and annotated a sample of 5,496 tweets to distinguish between personal use CBD tweets and commercial/sales-related CBD tweets. We used this sample to train two binary text classifiers to create two corpora of 169,876 personal use and 148,866 commercial/sales. Using medical, standard, and slang dictionaries, we then identified and compared the most frequently occurring medical conditions, symptoms, side effects, body parts, and other substances referenced in both corpora.

Original language	English
Title of host publication	Mediterranean Forum – Data Science Conference - First International Conference, MeFDATA 2020, Revised Selected Papers
Editors	Jasminka Hasic Telalovic, Mehmed Kantardzic
Pages	139-150
Number of pages	12
DOIs	https://doi.org/10.1007/978-3-030-72805-2_10
State	Published - 2021
Event	1st Mediterranean Forum - Data Science Conference, MeFDATA 2020 - Virtual, Online Duration: Oct 24 2020 → Oct 24 2020

Publication series

Name	Communications in Computer and Information Science
Volume	1343 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	1st Mediterranean Forum - Data Science Conference, MeFDATA 2020
City	Virtual, Online
Period	10/24/20 → 10/24/20

Bibliographical note

Publisher Copyright:
© 2021, Springer Nature Switzerland AG.

Keywords

Cannabis
Text classification
Text mining

ASJC Scopus subject areas

General Computer Science
General Mathematics

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-72805-2_10

Cite this

Turner, J. S., Kantardzic, M. M., & Vickers-Smith, R. (2021). Classification and Analysis of Personal and Commercial CBD Tweets. In J. Hasic Telalovic, & M. Kantardzic (Eds.), Mediterranean Forum – Data Science Conference - First International Conference, MeFDATA 2020, Revised Selected Papers (pp. 139-150). (Communications in Computer and Information Science; Vol. 1343 CCIS). https://doi.org/10.1007/978-3-030-72805-2_10

Turner, Jason S. ; Kantardzic, Mehmed M. ; Vickers-Smith, Rachel. / Classification and Analysis of Personal and Commercial CBD Tweets. Mediterranean Forum – Data Science Conference - First International Conference, MeFDATA 2020, Revised Selected Papers. editor / Jasminka Hasic Telalovic ; Mehmed Kantardzic. 2021. pp. 139-150 (Communications in Computer and Information Science).

@inproceedings{a53459d7e88745f4ab7ebef522e31fc6,

title = "Classification and Analysis of Personal and Commercial CBD Tweets",

abstract = "This study analyzes the differences in terms regarding cannabidiol (CBD) expressed by commercial sellers and personal users on Twitter. It demonstrates that data from social networks can be used by public health and medical researchers to compare the medical conditions targeted by those selling loosely-regulated substances such as CBD against the medical conditions that patients themselves are commonly treating with CBD. We collected 567,850 tweets by searching Twitter with the Tweepy Python package using the terms CBD and cannabidiol, and annotated a sample of 5,496 tweets to distinguish between personal use CBD tweets and commercial/sales-related CBD tweets. We used this sample to train two binary text classifiers to create two corpora of 169,876 personal use and 148,866 commercial/sales. Using medical, standard, and slang dictionaries, we then identified and compared the most frequently occurring medical conditions, symptoms, side effects, body parts, and other substances referenced in both corpora.",

keywords = "Cannabis, Text classification, Text mining",

author = "Turner, {Jason S.} and Kantardzic, {Mehmed M.} and Rachel Vickers-Smith",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; 1st Mediterranean Forum - Data Science Conference, MeFDATA 2020 ; Conference date: 24-10-2020 Through 24-10-2020",

year = "2021",

doi = "10.1007/978-3-030-72805-2_10",

language = "English",

isbn = "9783030728045",

series = "Communications in Computer and Information Science",

pages = "139--150",

editor = "{Hasic Telalovic}, Jasminka and Mehmed Kantardzic",

booktitle = "Mediterranean Forum – Data Science Conference - First International Conference, MeFDATA 2020, Revised Selected Papers",

}

Turner, JS, Kantardzic, MM & Vickers-Smith, R 2021, Classification and Analysis of Personal and Commercial CBD Tweets. in J Hasic Telalovic & M Kantardzic (eds), Mediterranean Forum – Data Science Conference - First International Conference, MeFDATA 2020, Revised Selected Papers. Communications in Computer and Information Science, vol. 1343 CCIS, pp. 139-150, 1st Mediterranean Forum - Data Science Conference, MeFDATA 2020, Virtual, Online, 10/24/20. https://doi.org/10.1007/978-3-030-72805-2_10

Classification and Analysis of Personal and Commercial CBD Tweets. / Turner, Jason S.; Kantardzic, Mehmed M.; Vickers-Smith, Rachel.
Mediterranean Forum – Data Science Conference - First International Conference, MeFDATA 2020, Revised Selected Papers. ed. / Jasminka Hasic Telalovic; Mehmed Kantardzic. 2021. p. 139-150 (Communications in Computer and Information Science; Vol. 1343 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Classification and Analysis of Personal and Commercial CBD Tweets

AU - Turner, Jason S.

AU - Kantardzic, Mehmed M.

AU - Vickers-Smith, Rachel

PY - 2021

Y1 - 2021

N2 - This study analyzes the differences in terms regarding cannabidiol (CBD) expressed by commercial sellers and personal users on Twitter. It demonstrates that data from social networks can be used by public health and medical researchers to compare the medical conditions targeted by those selling loosely-regulated substances such as CBD against the medical conditions that patients themselves are commonly treating with CBD. We collected 567,850 tweets by searching Twitter with the Tweepy Python package using the terms CBD and cannabidiol, and annotated a sample of 5,496 tweets to distinguish between personal use CBD tweets and commercial/sales-related CBD tweets. We used this sample to train two binary text classifiers to create two corpora of 169,876 personal use and 148,866 commercial/sales. Using medical, standard, and slang dictionaries, we then identified and compared the most frequently occurring medical conditions, symptoms, side effects, body parts, and other substances referenced in both corpora.

AB - This study analyzes the differences in terms regarding cannabidiol (CBD) expressed by commercial sellers and personal users on Twitter. It demonstrates that data from social networks can be used by public health and medical researchers to compare the medical conditions targeted by those selling loosely-regulated substances such as CBD against the medical conditions that patients themselves are commonly treating with CBD. We collected 567,850 tweets by searching Twitter with the Tweepy Python package using the terms CBD and cannabidiol, and annotated a sample of 5,496 tweets to distinguish between personal use CBD tweets and commercial/sales-related CBD tweets. We used this sample to train two binary text classifiers to create two corpora of 169,876 personal use and 148,866 commercial/sales. Using medical, standard, and slang dictionaries, we then identified and compared the most frequently occurring medical conditions, symptoms, side effects, body parts, and other substances referenced in both corpora.

KW - Cannabis

KW - Text classification

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=85107424581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85107424581&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-72805-2_10

DO - 10.1007/978-3-030-72805-2_10

M3 - Conference contribution

AN - SCOPUS:85107424581

SN - 9783030728045

T3 - Communications in Computer and Information Science

SP - 139

EP - 150

BT - Mediterranean Forum – Data Science Conference - First International Conference, MeFDATA 2020, Revised Selected Papers

A2 - Hasic Telalovic, Jasminka

A2 - Kantardzic, Mehmed

T2 - 1st Mediterranean Forum - Data Science Conference, MeFDATA 2020

Y2 - 24 October 2020 through 24 October 2020

ER -

Turner JS, Kantardzic MM, Vickers-Smith R. Classification and Analysis of Personal and Commercial CBD Tweets. In Hasic Telalovic J, Kantardzic M, editors, Mediterranean Forum – Data Science Conference - First International Conference, MeFDATA 2020, Revised Selected Papers. 2021. p. 139-150. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-72805-2_10

Classification and Analysis of Personal and Commercial CBD Tweets

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this