Building and Validating Hierarchical Lexicons with a Case Study on Personal Values

Steven Wilson; Yiting Shen; Rada Mihalcea

doi:10.1007/978-3-030-01129-1_28

Building and Validating Hierarchical Lexicons with a Case Study on Personal Values

Steven Wilson, Yiting Shen, Rada Mihalcea

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

Abstract

We introduce a crowd-powered approach for the creation of a lexicon for any theme given a set of seed words that cover a variety of concepts within the theme. Terms are initially sorted by automatically clustering their embeddings and subsequently rearranged by crowd workers in order to create a tree structure. This type of organization captures hierarchical relationships between concepts and allows for a tunable level of specificity when using the lexicon to collect measurements from a piece of text. We use a lexicon expansion method to increase the overall coverage of the produced resource. Using our proposed approach, we create a hierarchical lexicon of personal values and evaluate its internal and external consistency. We release this novel resource to the community as a tool for measuring value content within text corpora.

Original language	English
Title of host publication	Social Informatics
Editors	Steffen Staab, Olessia Koltsova, Dmitry I. Ignatov
Place of Publication	Cham
Publisher	Springer
Pages	455-470
Number of pages	16
ISBN (Electronic)	978-3-030-01129-1
ISBN (Print)	978-3-030-01128-4
DOIs	https://doi.org/10.1007/978-3-030-01129-1_28
Publication status	Published - 20 Sept 2018
Event	10th International Conference on Social Informatics 2018 - Saint Petersburg, Russian Federation Duration: 25 Sept 2018 → 28 Sept 2018 https://socinfo2018.hse.ru/

Publication series

Name	Lecture Notes in Computer Science (LCNS)
Publisher	Springer, Cham
Volume	11185
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	10th International Conference on Social Informatics 2018
Abbreviated title	SocInfo 2018
Country/Territory	Russian Federation
City	Saint Petersburg
Period	25/09/18 → 28/09/18
Internet address	https://socinfo2018.hse.ru/

Keywords / Materials (for Non-textual outputs)

Lexicon induction
Crowd sourcing
Personal values

Access to Document

10.1007/978-3-030-01129-1_28Licence: All Rights Reserved

https://link.springer.com/chapter/10.1007/978-3-030-01129-1_28#copyrightInformationLicence: All Rights Reserved

Cite this

@inproceedings{89b26068890444aa88b4a15afe36625c,

title = "Building and Validating Hierarchical Lexicons with a Case Study on Personal Values",

abstract = "We introduce a crowd-powered approach for the creation of a lexicon for any theme given a set of seed words that cover a variety of concepts within the theme. Terms are initially sorted by automatically clustering their embeddings and subsequently rearranged by crowd workers in order to create a tree structure. This type of organization captures hierarchical relationships between concepts and allows for a tunable level of specificity when using the lexicon to collect measurements from a piece of text. We use a lexicon expansion method to increase the overall coverage of the produced resource. Using our proposed approach, we create a hierarchical lexicon of personal values and evaluate its internal and external consistency. We release this novel resource to the community as a tool for measuring value content within text corpora.",

keywords = "Lexicon induction, Crowd sourcing, Personal values",

author = "Steven Wilson and Yiting Shen and Rada Mihalcea",

year = "2018",

month = sep,

day = "20",

doi = "10.1007/978-3-030-01129-1_28",

language = "English",

isbn = "978-3-030-01128-4",

series = "Lecture Notes in Computer Science (LCNS)",

publisher = "Springer",

pages = "455--470",

editor = "Steffen Staab and Olessia Koltsova and Ignatov, {Dmitry I.}",

booktitle = "Social Informatics",

address = "United Kingdom",

note = "10th International Conference on Social Informatics 2018, SocInfo 2018 ; Conference date: 25-09-2018 Through 28-09-2018",

url = "https://socinfo2018.hse.ru/",

}

Wilson, S, Shen, Y & Mihalcea, R 2018, Building and Validating Hierarchical Lexicons with a Case Study on Personal Values. in S Staab, O Koltsova & DI Ignatov (eds), Social Informatics. Lecture Notes in Computer Science (LCNS), vol. 11185, Springer, Cham, pp. 455-470, 10th International Conference on Social Informatics 2018, Saint Petersburg, Russian Federation, 25/09/18. https://doi.org/10.1007/978-3-030-01129-1_28

Building and Validating Hierarchical Lexicons with a Case Study on Personal Values. / Wilson, Steven; Shen, Yiting; Mihalcea, Rada.
Social Informatics. ed. / Steffen Staab; Olessia Koltsova; Dmitry I. Ignatov. Cham: Springer, 2018. p. 455-470 (Lecture Notes in Computer Science (LCNS); Vol. 11185).

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

TY - GEN

T1 - Building and Validating Hierarchical Lexicons with a Case Study on Personal Values

AU - Wilson, Steven

AU - Shen, Yiting

AU - Mihalcea, Rada

PY - 2018/9/20

Y1 - 2018/9/20

N2 - We introduce a crowd-powered approach for the creation of a lexicon for any theme given a set of seed words that cover a variety of concepts within the theme. Terms are initially sorted by automatically clustering their embeddings and subsequently rearranged by crowd workers in order to create a tree structure. This type of organization captures hierarchical relationships between concepts and allows for a tunable level of specificity when using the lexicon to collect measurements from a piece of text. We use a lexicon expansion method to increase the overall coverage of the produced resource. Using our proposed approach, we create a hierarchical lexicon of personal values and evaluate its internal and external consistency. We release this novel resource to the community as a tool for measuring value content within text corpora.

AB - We introduce a crowd-powered approach for the creation of a lexicon for any theme given a set of seed words that cover a variety of concepts within the theme. Terms are initially sorted by automatically clustering their embeddings and subsequently rearranged by crowd workers in order to create a tree structure. This type of organization captures hierarchical relationships between concepts and allows for a tunable level of specificity when using the lexicon to collect measurements from a piece of text. We use a lexicon expansion method to increase the overall coverage of the produced resource. Using our proposed approach, we create a hierarchical lexicon of personal values and evaluate its internal and external consistency. We release this novel resource to the community as a tool for measuring value content within text corpora.

KW - Lexicon induction

KW - Crowd sourcing

KW - Personal values

UR - https://github.com/steve-wilson/values_lexicon/tree/master/code

UR - https://github.com/steve-wilson/values_lexicon/tree/master/lexicon_1_0

U2 - 10.1007/978-3-030-01129-1_28

DO - 10.1007/978-3-030-01129-1_28

M3 - Conference contribution

SN - 978-3-030-01128-4

T3 - Lecture Notes in Computer Science (LCNS)

SP - 455

EP - 470

BT - Social Informatics

A2 - Staab, Steffen

A2 - Koltsova, Olessia

A2 - Ignatov, Dmitry I.

PB - Springer

CY - Cham

T2 - 10th International Conference on Social Informatics 2018

Y2 - 25 September 2018 through 28 September 2018

ER -

Building and Validating Hierarchical Lexicons with a Case Study on Personal Values

Abstract

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

Cite this