Classification of intangible social innovation concepts

Nikola Milosevic, Abdullah Gök, Goran Nenadic

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

1 Citation (Scopus)

Abstract

In social sciences, similarly to other fields, there is exponential growth of literature and textual data that people are no more able to cope with in a systematic manner. In many areas there is a need to catalogue knowledge and phenomena in a certain area. However, social science concepts and phenomena are complex and in many cases there is a dispute in the field between conflicting definitions. In this paper we present a method that catalogues a complex and disputed concept of social innovation by applying text mining and machine learning techniques. Recognition of social innovations is performed by decomposing a definitions into several more specific criteria (social objectives, social actor interactions, outputs and innovativeness). For each of these criteria, a machine learning-based classifier is created that checks whether certain text satisfies given criteria. The criteria can be successfully classified with an F1-score of 0.83–0.86. The presented method is flexible, since it allows combining criteria in a later stage in order to build and analyse the definition of choice.
Original languageEnglish
Title of host publicationNatural Language Processing and Information Systems (NLDB 2018)
PublisherSpringer
Pages407-418
Number of pages12
Volume10859
ISBN (Print)9783319919461
DOIs
Publication statusPublished - 13 Jun 2018

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10859

Fingerprint

innovation
social science
social actor
learning
interaction

Keywords

  • text mining
  • classification
  • natural language processing
  • social innovation

Cite this

Milosevic, N., Gök, A., & Nenadic, G. (2018). Classification of intangible social innovation concepts. In Natural Language Processing and Information Systems (NLDB 2018) (Vol. 10859, pp. 407-418). (Lecture Notes in Computer Science; Vol. 10859). Springer. https://doi.org/10.1007/978-3-319-91947-8_42
Milosevic, Nikola ; Gök, Abdullah ; Nenadic, Goran. / Classification of intangible social innovation concepts. Natural Language Processing and Information Systems (NLDB 2018). Vol. 10859 Springer, 2018. pp. 407-418 (Lecture Notes in Computer Science).
@inproceedings{220a305e959e442bae3c11aa2d0edcc1,
title = "Classification of intangible social innovation concepts",
abstract = "In social sciences, similarly to other fields, there is exponential growth of literature and textual data that people are no more able to cope with in a systematic manner. In many areas there is a need to catalogue knowledge and phenomena in a certain area. However, social science concepts and phenomena are complex and in many cases there is a dispute in the field between conflicting definitions. In this paper we present a method that catalogues a complex and disputed concept of social innovation by applying text mining and machine learning techniques. Recognition of social innovations is performed by decomposing a definitions into several more specific criteria (social objectives, social actor interactions, outputs and innovativeness). For each of these criteria, a machine learning-based classifier is created that checks whether certain text satisfies given criteria. The criteria can be successfully classified with an F1-score of 0.83–0.86. The presented method is flexible, since it allows combining criteria in a later stage in order to build and analyse the definition of choice.",
keywords = "text mining, classification, natural language processing, social innovation",
author = "Nikola Milosevic and Abdullah G{\"o}k and Goran Nenadic",
year = "2018",
month = "6",
day = "13",
doi = "10.1007/978-3-319-91947-8_42",
language = "English",
isbn = "9783319919461",
volume = "10859",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "407--418",
booktitle = "Natural Language Processing and Information Systems (NLDB 2018)",

}

Milosevic, N, Gök, A & Nenadic, G 2018, Classification of intangible social innovation concepts. in Natural Language Processing and Information Systems (NLDB 2018). vol. 10859, Lecture Notes in Computer Science, vol. 10859, Springer, pp. 407-418. https://doi.org/10.1007/978-3-319-91947-8_42

Classification of intangible social innovation concepts. / Milosevic, Nikola; Gök, Abdullah; Nenadic, Goran.

Natural Language Processing and Information Systems (NLDB 2018). Vol. 10859 Springer, 2018. p. 407-418 (Lecture Notes in Computer Science; Vol. 10859).

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Classification of intangible social innovation concepts

AU - Milosevic, Nikola

AU - Gök, Abdullah

AU - Nenadic, Goran

PY - 2018/6/13

Y1 - 2018/6/13

N2 - In social sciences, similarly to other fields, there is exponential growth of literature and textual data that people are no more able to cope with in a systematic manner. In many areas there is a need to catalogue knowledge and phenomena in a certain area. However, social science concepts and phenomena are complex and in many cases there is a dispute in the field between conflicting definitions. In this paper we present a method that catalogues a complex and disputed concept of social innovation by applying text mining and machine learning techniques. Recognition of social innovations is performed by decomposing a definitions into several more specific criteria (social objectives, social actor interactions, outputs and innovativeness). For each of these criteria, a machine learning-based classifier is created that checks whether certain text satisfies given criteria. The criteria can be successfully classified with an F1-score of 0.83–0.86. The presented method is flexible, since it allows combining criteria in a later stage in order to build and analyse the definition of choice.

AB - In social sciences, similarly to other fields, there is exponential growth of literature and textual data that people are no more able to cope with in a systematic manner. In many areas there is a need to catalogue knowledge and phenomena in a certain area. However, social science concepts and phenomena are complex and in many cases there is a dispute in the field between conflicting definitions. In this paper we present a method that catalogues a complex and disputed concept of social innovation by applying text mining and machine learning techniques. Recognition of social innovations is performed by decomposing a definitions into several more specific criteria (social objectives, social actor interactions, outputs and innovativeness). For each of these criteria, a machine learning-based classifier is created that checks whether certain text satisfies given criteria. The criteria can be successfully classified with an F1-score of 0.83–0.86. The presented method is flexible, since it allows combining criteria in a later stage in order to build and analyse the definition of choice.

KW - text mining

KW - classification

KW - natural language processing

KW - social innovation

U2 - 10.1007/978-3-319-91947-8_42

DO - 10.1007/978-3-319-91947-8_42

M3 - Conference contribution book

SN - 9783319919461

VL - 10859

T3 - Lecture Notes in Computer Science

SP - 407

EP - 418

BT - Natural Language Processing and Information Systems (NLDB 2018)

PB - Springer

ER -

Milosevic N, Gök A, Nenadic G. Classification of intangible social innovation concepts. In Natural Language Processing and Information Systems (NLDB 2018). Vol. 10859. Springer. 2018. p. 407-418. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-91947-8_42