Improving Topic Model Clustering of Newspaper Comments for Summarisation

Clare Llewellyn; Claire Grover; Jon Oberlander

doi:10.18653/v1/P16-3007

Improving Topic Model Clustering of Newspaper Comments for Summarisation

Clare Llewellyn
, Claire Grover
, Jon Oberlander

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

Abstract

Online newspaper articles can accumulate comments at volumes that prevent close reading. Summarisation of the comments allows interaction at a higher level and can lead to an understanding of the overall discussion. Comment summarisation requires topic clustering, comment ranking and extraction. Clustering must be robust as the subsequent extraction relies on a good set of clusters. Comment data, as with many social media datasets, contains very short documents and the number of words in the documents is a limiting factors on the performance of LDA clustering. We evaluate whether we can combine comments to form larger documents to improve the quality of clusters. We find that combining comments with comments that reply to them produce the highest quality clusters.

Original language	English
Title of host publication	Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop
Publisher	Association for Computational Linguistics
Pages	43-50
Number of pages	8
ISBN (Print)	978-1-945626-02-9
DOIs	https://doi.org/10.18653/v1/P16-3007
Publication status	E-pub ahead of print - 12 Aug 2016
Event	54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop - Berlin, Germany Duration: 7 Aug 2016 → 12 Aug 2016

Conference

Conference	54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop
Abbreviated title	ACL 2016
Country/Territory	Germany
City	Berlin
Period	7/08/16 → 12/08/16

Access to Document

10.18653/v1/P16-3007

lrecFinalAccepted author manuscript, 348 KB
P16-3007Final published version, 124 KB

http://www.aclweb.org/anthology/P16-3007

Cite this

@inproceedings{73bb8a22a19f4bcaa3d809bdfeaef4a5,

title = "Improving Topic Model Clustering of Newspaper Comments for Summarisation",

abstract = "Online newspaper articles can accumulate comments at volumes that prevent close reading. Summarisation of the comments allows interaction at a higher level and can lead to an understanding of the overall discussion. Comment summarisation requires topic clustering, comment ranking and extraction. Clustering must be robust as the subsequent extraction relies on a good set of clusters. Comment data, as with many social media datasets, contains very short documents and the number of words in the documents is a limiting factors on the performance of LDA clustering. We evaluate whether we can combine comments to form larger documents to improve the quality of clusters. We find that combining comments with comments that reply to them produce the highest quality clusters.",

author = "Clare Llewellyn and Claire Grover and Jon Oberlander",

year = "2016",

month = aug,

day = "12",

doi = "10.18653/v1/P16-3007",

language = "English",

isbn = "978-1-945626-02-9",

pages = "43--50",

booktitle = "Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop",

publisher = "Association for Computational Linguistics",

note = "54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop, ACL 2016 ; Conference date: 07-08-2016 Through 12-08-2016",

}

Llewellyn, C, Grover, C & Oberlander, J 2016, Improving Topic Model Clustering of Newspaper Comments for Summarisation. in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop. Association for Computational Linguistics, pp. 43-50, 54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop, Berlin, Berlin, Germany, 7/08/16. https://doi.org/10.18653/v1/P16-3007

Improving Topic Model Clustering of Newspaper Comments for Summarisation. / Llewellyn, Clare; Grover, Claire; Oberlander, Jon.
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop. Association for Computational Linguistics, 2016. p. 43-50.

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

TY - GEN

T1 - Improving Topic Model Clustering of Newspaper Comments for Summarisation

AU - Llewellyn, Clare

AU - Grover, Claire

AU - Oberlander, Jon

PY - 2016/8/12

Y1 - 2016/8/12

N2 - Online newspaper articles can accumulate comments at volumes that prevent close reading. Summarisation of the comments allows interaction at a higher level and can lead to an understanding of the overall discussion. Comment summarisation requires topic clustering, comment ranking and extraction. Clustering must be robust as the subsequent extraction relies on a good set of clusters. Comment data, as with many social media datasets, contains very short documents and the number of words in the documents is a limiting factors on the performance of LDA clustering. We evaluate whether we can combine comments to form larger documents to improve the quality of clusters. We find that combining comments with comments that reply to them produce the highest quality clusters.

AB - Online newspaper articles can accumulate comments at volumes that prevent close reading. Summarisation of the comments allows interaction at a higher level and can lead to an understanding of the overall discussion. Comment summarisation requires topic clustering, comment ranking and extraction. Clustering must be robust as the subsequent extraction relies on a good set of clusters. Comment data, as with many social media datasets, contains very short documents and the number of words in the documents is a limiting factors on the performance of LDA clustering. We evaluate whether we can combine comments to form larger documents to improve the quality of clusters. We find that combining comments with comments that reply to them produce the highest quality clusters.

U2 - 10.18653/v1/P16-3007

DO - 10.18653/v1/P16-3007

M3 - Conference contribution

SN - 978-1-945626-02-9

SP - 43

EP - 50

BT - Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop

PB - Association for Computational Linguistics

T2 - 54th Annual Meeting of the Association for Computational Linguistics – Student Research Workshop

Y2 - 7 August 2016 through 12 August 2016

ER -

Improving Topic Model Clustering of Newspaper Comments for Summarisation

Abstract

Conference

Access to Document

Fingerprint

Cite this