Sentiment classification of tweets using hierarchical classification

Afroze Ibrahim Baqapuri; Saad Saleh; Muhammad U. Ilyas; Muhammad Murtaza Khan; Ali Mustafa Qamar

doi:10.1109/ICC.2016.7511391

Sentiment classification of tweets using hierarchical classification

Afroze Ibrahim Baqapuri, Saad Saleh, Muhammad U. Ilyas, Muhammad Murtaza Khan, Ali Mustafa Qamar

Computer Science

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

Abstract

This paper addresses the problem of sentiment classification of short messages on microblogging platforms. We apply machine learning and pattern recognition techniques to design and implement a classification system for microblog messages assigning them into one of three classes: positive, negative or neutral. As part of this work, we contributed a dataset consisting of approximately 10, 000 tweets, each labeled on a five point sentiment scale by three different people. Experiments demonstrate a detection rate between approximately 70% and an average false alarm rate of approximately 18% across all three classes. The developed classifier has been made available for online use.

Original language	English
Title of host publication	2016 IEEE International Conference on Communications (ICC)
Publisher	IEEE
Pages	1-7
Number of pages	7
ISBN (Print)	978-1-4799-6665-3
DOIs	https://doi.org/10.1109/ICC.2016.7511391
Publication status	Published - 27 May 2016
Event	2016 IEEE International Conference on Communications (ICC) - Kuala Lumpur, Malaysia Duration: 22 May 2016 → 27 May 2016

Conference

Conference	2016 IEEE International Conference on Communications (ICC)
Period	22/05/16 → 27/05/16

Keywords

Twitter
Sentiment analysis
Computational modeling
Blogs
Tagging
Feature extraction
Uniform resource locators

Access to Document

10.1109/ICC.2016.7511391

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7511391

Cite this

@inproceedings{a753afcc76794e56bc9ece9170f44fd9,

title = "Sentiment classification of tweets using hierarchical classification",

abstract = "This paper addresses the problem of sentiment classification of short messages on microblogging platforms. We apply machine learning and pattern recognition techniques to design and implement a classification system for microblog messages assigning them into one of three classes: positive, negative or neutral. As part of this work, we contributed a dataset consisting of approximately 10, 000 tweets, each labeled on a five point sentiment scale by three different people. Experiments demonstrate a detection rate between approximately 70% and an average false alarm rate of approximately 18% across all three classes. The developed classifier has been made available for online use.",

keywords = "Twitter, Sentiment analysis, Computational modeling, Blogs, Tagging, Feature extraction, Uniform resource locators",

author = "Baqapuri, {Afroze Ibrahim} and Saad Saleh and Ilyas, {Muhammad U.} and Khan, {Muhammad Murtaza} and Qamar, {Ali Mustafa}",

year = "2016",

month = may,

day = "27",

doi = "10.1109/ICC.2016.7511391",

language = "English",

isbn = "978-1-4799-6665-3",

pages = "1--7",

booktitle = "2016 IEEE International Conference on Communications (ICC)",

publisher = "IEEE",

note = "2016 IEEE International Conference on Communications (ICC) ; Conference date: 22-05-2016 Through 27-05-2016",

}

TY - GEN

T1 - Sentiment classification of tweets using hierarchical classification

AU - Baqapuri, Afroze Ibrahim

AU - Saleh, Saad

AU - Ilyas, Muhammad U.

AU - Khan, Muhammad Murtaza

AU - Qamar, Ali Mustafa

PY - 2016/5/27

Y1 - 2016/5/27

N2 - This paper addresses the problem of sentiment classification of short messages on microblogging platforms. We apply machine learning and pattern recognition techniques to design and implement a classification system for microblog messages assigning them into one of three classes: positive, negative or neutral. As part of this work, we contributed a dataset consisting of approximately 10, 000 tweets, each labeled on a five point sentiment scale by three different people. Experiments demonstrate a detection rate between approximately 70% and an average false alarm rate of approximately 18% across all three classes. The developed classifier has been made available for online use.

AB - This paper addresses the problem of sentiment classification of short messages on microblogging platforms. We apply machine learning and pattern recognition techniques to design and implement a classification system for microblog messages assigning them into one of three classes: positive, negative or neutral. As part of this work, we contributed a dataset consisting of approximately 10, 000 tweets, each labeled on a five point sentiment scale by three different people. Experiments demonstrate a detection rate between approximately 70% and an average false alarm rate of approximately 18% across all three classes. The developed classifier has been made available for online use.

KW - Twitter

KW - Sentiment analysis

KW - Computational modeling

KW - Blogs

KW - Tagging

KW - Feature extraction

KW - Uniform resource locators

UR - https://ieeexplore.ieee.org/document/7511391/

U2 - 10.1109/ICC.2016.7511391

DO - 10.1109/ICC.2016.7511391

M3 - Conference contribution

SN - 978-1-4799-6665-3

SP - 1

EP - 7

BT - 2016 IEEE International Conference on Communications (ICC)

PB - IEEE

T2 - 2016 IEEE International Conference on Communications (ICC)

Y2 - 22 May 2016 through 27 May 2016

ER -

Sentiment classification of tweets using hierarchical classification

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this