Optimising Agile Social Media Analysis

Thomas Kober; David Weir

doi:10.18653/v1/W15-2906

Optimising Agile Social Media Analysis

Thomas Kober, David Weir

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

Abstract / Description of output

Agile social media analysis involves building bespoke, one-off classification pipelines tailored to the analysis of specific datasets. In this study we investigate how the DUALIST architecture can be optimised for agile social media analysis. We evaluate several semi-supervised learning algorithms in conjunction with a Naïve Bayes model, and show how these modifications can improve the performance of bespoke classifiers for a variety of tasks on a large range of datasets.

Original language	English
Title of host publication	Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Publisher	Association for Computational Linguistics
Pages	31-40
Number of pages	10
DOIs	https://doi.org/10.18653/v1/W15-2906
Publication status	Published - 2015
Event	6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis - Lisbon, Portugal Duration: 17 Sept 2015 → … https://wt-public.emm4u.eu/wassa2015/index.htm?opc=0

Workshop

Workshop	6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Abbreviated title	WASSA 2015
Country/Territory	Portugal
City	Lisbon
Period	17/09/15 → …
Internet address	https://wt-public.emm4u.eu/wassa2015/index.htm?opc=0

Access to Document

10.18653/v1/W15-2906

http://www.aclweb.org/anthology/W15-2906

Cite this

@inproceedings{51f1b83ee2714ed0be1807eee5d89c2f,

title = "Optimising Agile Social Media Analysis",

abstract = "Agile social media analysis involves building bespoke, one-off classification pipelines tailored to the analysis of specific datasets. In this study we investigate how the DUALIST architecture can be optimised for agile social media analysis. We evaluate several semi-supervised learning algorithms in conjunction with a Na{\"i}ve Bayes model, and show how these modifications can improve the performance of bespoke classifiers for a variety of tasks on a large range of datasets.",

author = "Thomas Kober and David Weir",

year = "2015",

doi = "10.18653/v1/W15-2906",

language = "English",

pages = "31--40",

booktitle = "Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",

publisher = "Association for Computational Linguistics",

note = "6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2015 ; Conference date: 17-09-2015",

url = "https://wt-public.emm4u.eu/wassa2015/index.htm?opc=0",

}

Kober, T & Weir, D 2015, Optimising Agile Social Media Analysis. in Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. Association for Computational Linguistics, pp. 31-40, 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Lisbon, Portugal, 17/09/15. https://doi.org/10.18653/v1/W15-2906

TY - GEN

T1 - Optimising Agile Social Media Analysis

AU - Kober, Thomas

AU - Weir, David

PY - 2015

Y1 - 2015

N2 - Agile social media analysis involves building bespoke, one-off classification pipelines tailored to the analysis of specific datasets. In this study we investigate how the DUALIST architecture can be optimised for agile social media analysis. We evaluate several semi-supervised learning algorithms in conjunction with a Naïve Bayes model, and show how these modifications can improve the performance of bespoke classifiers for a variety of tasks on a large range of datasets.

AB - Agile social media analysis involves building bespoke, one-off classification pipelines tailored to the analysis of specific datasets. In this study we investigate how the DUALIST architecture can be optimised for agile social media analysis. We evaluate several semi-supervised learning algorithms in conjunction with a Naïve Bayes model, and show how these modifications can improve the performance of bespoke classifiers for a variety of tasks on a large range of datasets.

U2 - 10.18653/v1/W15-2906

DO - 10.18653/v1/W15-2906

M3 - Conference contribution

SP - 31

EP - 40

BT - Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

PB - Association for Computational Linguistics

T2 - 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

Y2 - 17 September 2015

ER -

Optimising Agile Social Media Analysis

Abstract / Description of output

Workshop

Access to Document

Fingerprint

Cite this