Developing a rule-based method for identifying researchers on Twitter: The case of vaccine discussions

Creator/Principal investigator(s):

Description:

This study seeks to develop a method for identifying the occurrences and proportions of researchers, media and other professionals active in Twitter discussions. As a case example, an anonymised dataset from Twitter vaccine discussions is used. The study proposes a method of using keywords as strings within lists to identify classes from user biographies. This provides a way to apply multiple classification principles to a set of Twitter biographies using semantic rules through the Python programming language. The script used for the study is here deposited.

Subject area:

information society, language and linguistics, higher and further education (CESSDA Topic Classification)
Information Studies, Social Sciences, Language Technology (Computational Linguistics) (The Swedish standard of fields of research 2011)

Keywords:

social media, classification

Principal organisation:

University of Borås

Accessibility status:

Access to data through SND
Data are freely accessible

Download data:

class.py (7.62 KB)
Rule-based method for identifying researchers on Twitter

Responsible department/unit:

Creator/Principal investigator(s):

Identifiers:

SND-ID: SND 1117

Description:

This study seeks to develop a method for identifying the occurrences and proportions of researchers, media and other professionals active in Twitter discussions. As a case example, an anonymised dataset from Twitter vaccine discussions is used. The study proposes a method of using keywords as strings within lists to identify classes from user biographies. This provides a way to apply multiple classification principles to a set of Twitter biographies using semantic rules through the Python programming language. The script used for the study is here deposited.

Language:

English

Time period(s) investigated:

2018-06-01 — 2019-10-31

Unit of analysis:

Population:

Twitter users

Time Method:

Sampling procedure:

Other

Funding:

Horizon 2020 —770531

Subject area:

information society, language and linguistics, higher and further education (CESSDA Topic Classification)
Information Studies, Social Sciences, Language Technology (Computational Linguistics) (The Swedish standard of fields of research 2011)

Keywords:

social media, classification

Download metadata:

Publications

Sort by name | Sort by year

Ekström, B. (2019). Developing a rule-based method for identifying researchers on Twitter: The case of vaccine discussions. Poster abstract accepted to ISSI, 17th International Society of Scientometrics and Informetrics Conference, Rome, 2-5 September.

If you have published anything based on these data, please notify us with a reference to your publication(s).

Version 1.0:

2019-08-23 doi:10.5878/akmc-va16

Download data:

class.py (7.62 KB)
Rule-based method for identifying researchers on Twitter

License:

Creative Commons License

Rule-based method for identifying researchers on Twitter

Citation:

Björn Ekström. University of Borås (2019). Rule-based method for identifying researchers on Twitter. Swedish National Data Service. Version 1.0. https://doi.org/10.5878/akmc-va16

Description:

Method development for Twitter biography classification concerning occurrences of academics, academically related groups and individuals, media, other groups and members of the general public. Written in the Python programming language.

Data format / data structure:

Software