Helping users discover perspectives: Enhancing opinion mining with joint topic models

Tim Draws; Jody Liu; Nava Tintarev

doi:10.1109/ICDMW51313.2020.00013

Helping users discover perspectives: Enhancing opinion mining with joint topic models

Tim Draws, Jody Liu, Nava Tintarev

Web Information Systems

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

3 Citations (Scopus)

46 Downloads (Pure)

Abstract

Support or opposition concerning a debated claim such as abortion should be legal can have different underlying reasons, which we call perspectives. This paper explores how opinion mining can be enhanced with joint topic modeling, to identify distinct perspectives within the topic, providing an informative overview from unstructured text. We evaluate four joint topic models (TAM, JST, VODUM, and LAM) in a user study assessing human understandability of the extracted perspectives. Based on the results, we conclude that joint topic models such as TAM can discover perspectives that align with human judgments. Moreover, our results suggest that users are not influenced by their pre-existing stance on the topic of abortion when interpreting the output of topic models.

Original language	English
Title of host publication	2020 International Conference on Data Mining Workshops (ICDMW)
Editors	L. O'Conner
Place of Publication	Piscataway
Publisher	IEEE
Pages	23-30
Number of pages	8
ISBN (Electronic)	978-1-7281-9012-9
ISBN (Print)	978-1-7281-9013-6
DOIs	https://doi.org/10.1109/ICDMW51313.2020.00013
Publication status	Published - 2021
Event	International Conference on Data Mining Workshops 2020 - Virtual/online event due to COVID-19, Sorrento, Italy Duration: 2 Dec 2020 → 2 Dec 2020

Conference

Conference	International Conference on Data Mining Workshops 2020
Abbreviated title	ICDMW 2020
Country/Territory	Italy
City	Sorrento
Period	2/12/20 → 2/12/20

Bibliographical note

Virtual/online event due to COVID-19

Keywords

debated topics
joint topic models
perspective discovery
sentiment analysis
topic modeling

Access to Document

10.1109/ICDMW51313.2020.00013

Helping_users_discover_perspectives_in_controversial_debates_using_joint_topic_modelsAccepted author manuscript, 356 KB

Cite this

@inproceedings{426eee202d7d43b2b4057623a1c26343,

title = "Helping users discover perspectives: Enhancing opinion mining with joint topic models",

abstract = "Support or opposition concerning a debated claim such as abortion should be legal can have different underlying reasons, which we call perspectives. This paper explores how opinion mining can be enhanced with joint topic modeling, to identify distinct perspectives within the topic, providing an informative overview from unstructured text. We evaluate four joint topic models (TAM, JST, VODUM, and LAM) in a user study assessing human understandability of the extracted perspectives. Based on the results, we conclude that joint topic models such as TAM can discover perspectives that align with human judgments. Moreover, our results suggest that users are not influenced by their pre-existing stance on the topic of abortion when interpreting the output of topic models.",

keywords = "debated topics, joint topic models, perspective discovery, sentiment analysis, topic modeling",

author = "Tim Draws and Jody Liu and Nava Tintarev",

note = "Virtual/online event due to COVID-19; International Conference on Data Mining Workshops 2020, ICDMW 2020 ; Conference date: 02-12-2020 Through 02-12-2020",

year = "2021",

doi = "10.1109/ICDMW51313.2020.00013",

language = "English",

isbn = "978-1-7281-9013-6",

pages = "23--30",

editor = "L. O'Conner",

booktitle = "2020 International Conference on Data Mining Workshops (ICDMW)",

publisher = "IEEE",

address = "United States",

}

Draws, T, Liu, J & Tintarev, N 2021, Helping users discover perspectives: Enhancing opinion mining with joint topic models. in L O'Conner (ed.), 2020 International Conference on Data Mining Workshops (ICDMW)., 9346407, IEEE, Piscataway, pp. 23-30, International Conference on Data Mining Workshops 2020, Sorrento, Italy, 2/12/20. https://doi.org/10.1109/ICDMW51313.2020.00013

Helping users discover perspectives: Enhancing opinion mining with joint topic models. / Draws, Tim; Liu, Jody; Tintarev, Nava.
2020 International Conference on Data Mining Workshops (ICDMW). ed. / L. O'Conner. Piscataway: IEEE, 2021. p. 23-30 9346407.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Helping users discover perspectives

T2 - International Conference on Data Mining Workshops 2020

AU - Draws, Tim

AU - Liu, Jody

AU - Tintarev, Nava

N1 - Virtual/online event due to COVID-19

PY - 2021

Y1 - 2021

N2 - Support or opposition concerning a debated claim such as abortion should be legal can have different underlying reasons, which we call perspectives. This paper explores how opinion mining can be enhanced with joint topic modeling, to identify distinct perspectives within the topic, providing an informative overview from unstructured text. We evaluate four joint topic models (TAM, JST, VODUM, and LAM) in a user study assessing human understandability of the extracted perspectives. Based on the results, we conclude that joint topic models such as TAM can discover perspectives that align with human judgments. Moreover, our results suggest that users are not influenced by their pre-existing stance on the topic of abortion when interpreting the output of topic models.

AB - Support or opposition concerning a debated claim such as abortion should be legal can have different underlying reasons, which we call perspectives. This paper explores how opinion mining can be enhanced with joint topic modeling, to identify distinct perspectives within the topic, providing an informative overview from unstructured text. We evaluate four joint topic models (TAM, JST, VODUM, and LAM) in a user study assessing human understandability of the extracted perspectives. Based on the results, we conclude that joint topic models such as TAM can discover perspectives that align with human judgments. Moreover, our results suggest that users are not influenced by their pre-existing stance on the topic of abortion when interpreting the output of topic models.

KW - debated topics

KW - joint topic models

KW - perspective discovery

KW - sentiment analysis

KW - topic modeling

UR - http://www.scopus.com/inward/record.url?scp=85101383162&partnerID=8YFLogxK

U2 - 10.1109/ICDMW51313.2020.00013

DO - 10.1109/ICDMW51313.2020.00013

M3 - Conference contribution

SN - 978-1-7281-9013-6

SP - 23

EP - 30

BT - 2020 International Conference on Data Mining Workshops (ICDMW)

A2 - O'Conner, L.

PB - IEEE

CY - Piscataway

Y2 - 2 December 2020 through 2 December 2020

ER -

Helping users discover perspectives: Enhancing opinion mining with joint topic models

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this