N-gram representations for comment filtering

D. Brand; St. Kroon; B. Van Der Merwe; L. Cleophas

doi:10.1145/2815782.2815789

N-gram representations for comment filtering

D. Brand
, St. Kroon
, B. Van Der Merwe
, L. Cleophas

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

1 Citation (Scopus)

1 Downloads (Pure)

Abstract

Accurate classifiers for short texts are valuable assets in many applications. Especially in online communities, where users contribute to content in the form of posts and com- ments, an effective way of automatically categorising posts proves highly valuable. This paper investigates the use of N- grams as features for short text classification, and compares it to manual feature design techniques that have been popu- lar in this domain. We find that the N-gram representations greatly outperform manual feature extraction techniques.

Original language	English
Title of host publication	SAICSIT '15 Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 28-30 September 2015, Stellenbosch, South Africa
Place of Publication	New York
Publisher	Association for Computing Machinery, Inc.
Pages	1-10
ISBN (Print)	9781450336833
DOIs	https://doi.org/10.1145/2815782.2815789
Publication status	Published - 28 Sept 2015
Event	2015 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists (SAICSIT 2015) - Stellenbosch Institute for Advanced Study (STIAS), Stellenbosch, South Africa Duration: 28 Sept 2015 → 30 Sept 2015 http://www.saicsit2015.org/

Conference

Conference	2015 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists (SAICSIT 2015)
Abbreviated title	SAICSIT 2015
Country/Territory	South Africa
City	Stellenbosch
Period	28/09/15 → 30/09/15
Other	"Knowledge through Technology"
Internet address	http://www.saicsit2015.org/

Keywords

Classification
Feature design
Information retrieval
N-gram models
NLP
Text mining
Vector space models

Access to Document

10.1145/2815782.2815789

Cite this

Brand, D., Kroon, S., Van Der Merwe, B., & Cleophas, L. (2015). N-gram representations for comment filtering. In SAICSIT '15 Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 28-30 September 2015, Stellenbosch, South Africa (pp. 1-10). Article 6 Association for Computing Machinery, Inc.. https://doi.org/10.1145/2815782.2815789

@inproceedings{a731a0391edd499d90f2fdd684902ab0,

title = "N-gram representations for comment filtering",

abstract = "Accurate classifiers for short texts are valuable assets in many applications. Especially in online communities, where users contribute to content in the form of posts and com- ments, an effective way of automatically categorising posts proves highly valuable. This paper investigates the use of N- grams as features for short text classification, and compares it to manual feature design techniques that have been popu- lar in this domain. We find that the N-gram representations greatly outperform manual feature extraction techniques.",

keywords = "Classification, Feature design, Information retrieval, N-gram models, NLP, Text mining, Vector space models",

author = "D. Brand and St. Kroon and \{Van Der Merwe\}, B. and L. Cleophas",

year = "2015",

month = sep,

day = "28",

doi = "10.1145/2815782.2815789",

language = "English",

isbn = "9781450336833",

pages = "1--10",

booktitle = "SAICSIT '15 Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 28-30 September 2015, Stellenbosch, South Africa",

publisher = "Association for Computing Machinery, Inc.",

address = "United States",

note = "2015 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists (SAICSIT 2015), SAICSIT 2015 ; Conference date: 28-09-2015 Through 30-09-2015",

url = "http://www.saicsit2015.org/",

}

Brand, D, Kroon, S, Van Der Merwe, B & Cleophas, L 2015, N-gram representations for comment filtering. in SAICSIT '15 Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 28-30 September 2015, Stellenbosch, South Africa ., 6, Association for Computing Machinery, Inc., New York, pp. 1-10, 2015 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists (SAICSIT 2015), Stellenbosch, South Africa, 28/09/15. https://doi.org/10.1145/2815782.2815789

N-gram representations for comment filtering. / Brand, D.; Kroon, St.; Van Der Merwe, B. et al.
SAICSIT '15 Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 28-30 September 2015, Stellenbosch, South Africa . New York: Association for Computing Machinery, Inc., 2015. p. 1-10 6.

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

TY - GEN

T1 - N-gram representations for comment filtering

AU - Brand, D.

AU - Kroon, St.

AU - Van Der Merwe, B.

AU - Cleophas, L.

PY - 2015/9/28

Y1 - 2015/9/28

N2 - Accurate classifiers for short texts are valuable assets in many applications. Especially in online communities, where users contribute to content in the form of posts and com- ments, an effective way of automatically categorising posts proves highly valuable. This paper investigates the use of N- grams as features for short text classification, and compares it to manual feature design techniques that have been popu- lar in this domain. We find that the N-gram representations greatly outperform manual feature extraction techniques.

AB - Accurate classifiers for short texts are valuable assets in many applications. Especially in online communities, where users contribute to content in the form of posts and com- ments, an effective way of automatically categorising posts proves highly valuable. This paper investigates the use of N- grams as features for short text classification, and compares it to manual feature design techniques that have been popu- lar in this domain. We find that the N-gram representations greatly outperform manual feature extraction techniques.

KW - Classification

KW - Feature design

KW - Information retrieval

KW - N-gram models

KW - NLP

KW - Text mining

KW - Vector space models

UR - https://www.scopus.com/pages/publications/84959374437

U2 - 10.1145/2815782.2815789

DO - 10.1145/2815782.2815789

M3 - Conference contribution

AN - SCOPUS:84959374437

SN - 9781450336833

SP - 1

EP - 10

BT - SAICSIT '15 Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 28-30 September 2015, Stellenbosch, South Africa

PB - Association for Computing Machinery, Inc.

CY - New York

T2 - 2015 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists (SAICSIT 2015)

Y2 - 28 September 2015 through 30 September 2015

ER -

Brand D, Kroon S, Van Der Merwe B, Cleophas L. N-gram representations for comment filtering. In SAICSIT '15 Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 28-30 September 2015, Stellenbosch, South Africa . New York: Association for Computing Machinery, Inc. 2015. p. 1-10. 6 doi: 10.1145/2815782.2815789

N-gram representations for comment filtering

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this