Using machine learning and text mining to classify fuzzy social science phenomenon: the case of social innovation

Abdullah Gök; Nikola Milosevic; Goran Nenadic

Using machine learning and text mining to classify fuzzy social science phenomenon: the case of social innovation

Abdullah Gök, Nikola Milosevic, Goran Nenadic

Hunter Centre For Entrepreneurship

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

1 Citation (Scopus)

76 Downloads (Pure)

Abstract

Classifying social science concepts by using machine learning and text-mining is often very challenging, particularly due to the fact that social concepts are often defined in a vague manner. In this paper, we put forward a first conceptual step to overcome this challenge. By using the case of social innovation, which has 252 distinct definitions, we qualitatively demonstrated that these definitions group around four different themes where various definitions utilise one or multiple of these criteria in different combinations to define social innovations. We designed an experiment where a database of social innovation projects annotated i) based on an overall understanding and ii) based on a decomposed definition of four criteria. As a next step, we will test the performance of various model specification on these two approaches.

Original language	English
Title of host publication	17th International Conference on Scientometrics and Informetrics, ISSI 2019
Subtitle of host publication	Proceedings : Volume II
Editors	Giuseppe Catalano, Cinzia Daraio, Martina Gregori, Henk F. Moed, Giancarlo Ruocco
Place of Publication	Italy
Pages	2171-2176
Number of pages	6
Publication status	Published - 31 Aug 2019
Event	17th International Conference on Scientometrics and Informetrics - Rome, Italy Duration: 2 Sept 2019 → 5 Sept 2019

Conference

Conference	17th International Conference on Scientometrics and Informetrics
Abbreviated title	ISSI 2019
Country/Territory	Italy
City	Rome
Period	2/09/19 → 5/09/19

Keywords

machine learning
text mining
social Innovation
scientometrics
informetrics

Access to Document

Gok-etal-ISSI-2019-Using-machine-learning-and-text-mining-to-classify-fuzzy-social-science-phenomenonFinal published version, 399 KB

Cite this

Gök, Abdullah ; Milosevic, Nikola ; Nenadic, Goran. / Using machine learning and text mining to classify fuzzy social science phenomenon : the case of social innovation. 17th International Conference on Scientometrics and Informetrics, ISSI 2019: Proceedings : Volume II. editor / Giuseppe Catalano ; Cinzia Daraio ; Martina Gregori ; Henk F. Moed ; Giancarlo Ruocco. Italy, 2019. pp. 2171-2176

@inproceedings{c23e3eee2ec847c4940f0b73db3de75d,

title = "Using machine learning and text mining to classify fuzzy social science phenomenon: the case of social innovation",

abstract = "Classifying social science concepts by using machine learning and text-mining is often very challenging, particularly due to the fact that social concepts are often defined in a vague manner. In this paper, we put forward a first conceptual step to overcome this challenge. By using the case of social innovation, which has 252 distinct definitions, we qualitatively demonstrated that these definitions group around four different themes where various definitions utilise one or multiple of these criteria in different combinations to define social innovations. We designed an experiment where a database of social innovation projects annotated i) based on an overall understanding and ii) based on a decomposed definition of four criteria. As a next step, we will test the performance of various model specification on these two approaches.",

keywords = "machine learning, text mining, social Innovation, scientometrics, informetrics",

author = "Abdullah G{\"o}k and Nikola Milosevic and Goran Nenadic",

year = "2019",

month = aug,

day = "31",

language = "English",

isbn = "9788833811185",

pages = "2171--2176",

editor = "Giuseppe Catalano and Cinzia Daraio and Martina Gregori and Moed, {Henk F.} and Giancarlo Ruocco",

booktitle = "17th International Conference on Scientometrics and Informetrics, ISSI 2019",

note = "17th International Conference on Scientometrics and Informetrics, ISSI 2019 ; Conference date: 02-09-2019 Through 05-09-2019",

}

Gök, A, Milosevic, N & Nenadic, G 2019, Using machine learning and text mining to classify fuzzy social science phenomenon: the case of social innovation. in G Catalano, C Daraio, M Gregori, HF Moed & G Ruocco (eds), 17th International Conference on Scientometrics and Informetrics, ISSI 2019: Proceedings : Volume II. Italy, pp. 2171-2176, 17th International Conference on Scientometrics and Informetrics, Rome, Italy, 2/09/19.

Using machine learning and text mining to classify fuzzy social science phenomenon: the case of social innovation. / Gök, Abdullah; Milosevic, Nikola; Nenadic, Goran.
17th International Conference on Scientometrics and Informetrics, ISSI 2019: Proceedings : Volume II. ed. / Giuseppe Catalano; Cinzia Daraio; Martina Gregori; Henk F. Moed; Giancarlo Ruocco. Italy, 2019. p. 2171-2176.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Using machine learning and text mining to classify fuzzy social science phenomenon

T2 - 17th International Conference on Scientometrics and Informetrics

AU - Gök, Abdullah

AU - Milosevic, Nikola

AU - Nenadic, Goran

PY - 2019/8/31

Y1 - 2019/8/31

N2 - Classifying social science concepts by using machine learning and text-mining is often very challenging, particularly due to the fact that social concepts are often defined in a vague manner. In this paper, we put forward a first conceptual step to overcome this challenge. By using the case of social innovation, which has 252 distinct definitions, we qualitatively demonstrated that these definitions group around four different themes where various definitions utilise one or multiple of these criteria in different combinations to define social innovations. We designed an experiment where a database of social innovation projects annotated i) based on an overall understanding and ii) based on a decomposed definition of four criteria. As a next step, we will test the performance of various model specification on these two approaches.

AB - Classifying social science concepts by using machine learning and text-mining is often very challenging, particularly due to the fact that social concepts are often defined in a vague manner. In this paper, we put forward a first conceptual step to overcome this challenge. By using the case of social innovation, which has 252 distinct definitions, we qualitatively demonstrated that these definitions group around four different themes where various definitions utilise one or multiple of these criteria in different combinations to define social innovations. We designed an experiment where a database of social innovation projects annotated i) based on an overall understanding and ii) based on a decomposed definition of four criteria. As a next step, we will test the performance of various model specification on these two approaches.

KW - machine learning

KW - text mining

KW - social Innovation

KW - scientometrics

KW - informetrics

UR - http://www.issi-society.org/publications/issi-conference-proceedings/proceedings-of-issi-2019/

M3 - Conference contribution book

SN - 9788833811185

SP - 2171

EP - 2176

BT - 17th International Conference on Scientometrics and Informetrics, ISSI 2019

A2 - Catalano, Giuseppe

A2 - Daraio, Cinzia

A2 - Gregori, Martina

A2 - Moed, Henk F.

A2 - Ruocco, Giancarlo

CY - Italy

Y2 - 2 September 2019 through 5 September 2019

ER -

Using machine learning and text mining to classify fuzzy social science phenomenon: the case of social innovation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

KNOWMAK

Cite this

Using machine learning and text mining to classify fuzzy social science phenomenon: the case of social innovation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

KNOWMAK

Cite this