Towards automatic web identification of solutions in patient innovation

João N. Almeida; Salomé Azevedo; Joao P. Carvalho

doi:10.1007/978-3-030-16024-1_2

Towards automatic web identification of solutions in patient innovation

João N. Almeida, Salomé Azevedo, Joao P. Carvalho^*

^*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

Patient Innovation is an online open platform, with a community of over 60.000 users and more than 800 innovative solutions developed by patients and informal caregivers from all over the world. These solutions and/or creators were found by manually searching the Web in four different languages, through a combination of appropriate keywords and using experts to curate the results. In this paper we present a classifier architecture composed by a Word2Vec based SVM and a Fuzzy Fingerprint relevance classifier that is able to obtain a F1-score of 0.98 in the process of automatically identifying Patient Innovation solutions from texts obtained from the web.

Original language	English
Title of host publication	Studies in computational intelligence
Editors	László T. Kóczy, Jesús Medina-Moreno, Eloísa Ramírez-Poussa, Alexander Šostak
Place of Publication	Cham
Publisher	Springer Verlag
Pages	9-14
Number of pages	6
ISBN (Electronic)	9783030160241
ISBN (Print)	9783030160234
DOIs	https://doi.org/10.1007/978-3-030-16024-1_2
Publication status	Published - 2020

Publication series

Name	Studies in computational intelligence
Volume	819
ISSN (Print)	1860-949X

Keywords

Fuzzy fingerprints
Patient innovation
SVM
Text classification
Word2vec

Access to Document

10.1007/978-3-030-16024-1_2

Cite this

@inbook{174e2e587ab9431fa42d2a4d4985ecd7,

title = "Towards automatic web identification of solutions in patient innovation",

abstract = "Patient Innovation is an online open platform, with a community of over 60.000 users and more than 800 innovative solutions developed by patients and informal caregivers from all over the world. These solutions and/or creators were found by manually searching the Web in four different languages, through a combination of appropriate keywords and using experts to curate the results. In this paper we present a classifier architecture composed by a Word2Vec based SVM and a Fuzzy Fingerprint relevance classifier that is able to obtain a F1-score of 0.98 in the process of automatically identifying Patient Innovation solutions from texts obtained from the web.",

keywords = "Fuzzy fingerprints, Patient innovation, SVM, Text classification, Word2vec",

author = "Almeida, \{Jo{\~a}o N.\} and Salom{\'e} Azevedo and Carvalho, \{Joao P.\}",

year = "2020",

doi = "10.1007/978-3-030-16024-1\_2",

language = "English",

isbn = "9783030160234",

series = "Studies in computational intelligence",

publisher = "Springer Verlag",

pages = "9--14",

editor = "K{\'o}czy, \{L{\'a}szl{\'o} T.\} and Medina-Moreno, \{Jes{\'u}s \} and Elo{\'i}sa Ram{\'i}rez-Poussa and Alexander {\v S}ostak",

booktitle = "Studies in computational intelligence",

address = "Germany",

}

Towards automatic web identification of solutions in patient innovation. / Almeida, João N.; Azevedo, Salomé; Carvalho, Joao P.
Studies in computational intelligence. ed. / László T. Kóczy; Jesús Medina-Moreno; Eloísa Ramírez-Poussa; Alexander Šostak. Cham: Springer Verlag, 2020. p. 9-14 (Studies in computational intelligence; Vol. 819).

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

TY - CHAP

T1 - Towards automatic web identification of solutions in patient innovation

AU - Almeida, João N.

AU - Azevedo, Salomé

AU - Carvalho, Joao P.

PY - 2020

Y1 - 2020

N2 - Patient Innovation is an online open platform, with a community of over 60.000 users and more than 800 innovative solutions developed by patients and informal caregivers from all over the world. These solutions and/or creators were found by manually searching the Web in four different languages, through a combination of appropriate keywords and using experts to curate the results. In this paper we present a classifier architecture composed by a Word2Vec based SVM and a Fuzzy Fingerprint relevance classifier that is able to obtain a F1-score of 0.98 in the process of automatically identifying Patient Innovation solutions from texts obtained from the web.

AB - Patient Innovation is an online open platform, with a community of over 60.000 users and more than 800 innovative solutions developed by patients and informal caregivers from all over the world. These solutions and/or creators were found by manually searching the Web in four different languages, through a combination of appropriate keywords and using experts to curate the results. In this paper we present a classifier architecture composed by a Word2Vec based SVM and a Fuzzy Fingerprint relevance classifier that is able to obtain a F1-score of 0.98 in the process of automatically identifying Patient Innovation solutions from texts obtained from the web.

KW - Fuzzy fingerprints

KW - Patient innovation

KW - SVM

KW - Text classification

KW - Word2vec

UR - http://www.scopus.com/inward/record.url?scp=85066152735&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-16024-1_2

DO - 10.1007/978-3-030-16024-1_2

M3 - Chapter

AN - SCOPUS:85066152735

SN - 9783030160234

T3 - Studies in computational intelligence

SP - 9

EP - 14

BT - Studies in computational intelligence

A2 - Kóczy, László T.

A2 - Medina-Moreno, Jesús

A2 - Ramírez-Poussa, Eloísa

A2 - Šostak, Alexander

PB - Springer Verlag

CY - Cham

ER -

Towards automatic web identification of solutions in patient innovation

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

CUBE: Católica Lisbon Research Unit in Business and Economics

Cite this

Towards automatic web identification of solutions in patient innovation

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Projects

CUBE: Católica Lisbon Research Unit in Business and Economics

Cite this