Using Short URLs in Tweets to Improve Twitter Opinion Mining

Andrei Pavel; Vasile Palade; Rahat Iqbal; Diana Hintea

doi:10.1109/ICMLA.2017.00-28

Using Short URLs in Tweets to Improve Twitter Opinion Mining

Andrei Pavel, Vasile Palade, Rahat Iqbal, Diana Hintea

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

3 Citations (Scopus)

Abstract

Using short URLs in Twitter messages has increased in popularity in the past few years. This is mostly due to the fact that Twitter, as one of the most popular social media networks, imposes a 140 character limit to the messages distributed over the network. This paper analyzes the use of short URLs by Twitter users. Specifically, the goal is to examine the content pointed by the short URLs as well as the potential impact on the performance of sentiment analysis (opinion mining) tasks. Opinion mining based on Twitter feed has been used in an array of applications, including healthcare, identifying public opinion on political issues, financial modeling and advertising. Past research has however completely disregarded tweets which contain URLs. It is not hard to see how opinion mining can be improved considering the fact that Twitter users regularly post URLs pointing to articles endorsing a particular political figure, articles in important financial outlets or reviews of products. This study is based on the analysis of three distinct Twitter datasets with varying number of tweets which include short URLs. Popular machine learning techniques used in opinion mining were deployed in different experimental settings to conclude which are the most lucrative options. © 2017 IEEE.

Original language	English
Title of host publication	Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
Publisher	IEEE
Pages	965-970
Volume	2017-December
ISBN (Print)	978-153861417-4
DOIs	https://doi.org/10.1109/ICMLA.2017.00-28
Publication status	Published - Dec 2017
Event	16th IEEE International Conference on Machine Learning and Applications (ICMLA) - Mexico, Cancun, Mexico Duration: 18 Dec 2017 → 21 Dec 2017 http://www.icmla-conference.org/icmla17/

Conference

Conference	16th IEEE International Conference on Machine Learning and Applications (ICMLA)
Country/Territory	Mexico
City	Cancun
Period	18/12/17 → 21/12/17
Internet address	http://www.icmla-conference.org/icmla17/

Access to Document

10.1109/ICMLA.2017.00-28

Cite this

Pavel, A, Palade, V, Iqbal, R & Hintea, D 2017, Using Short URLs in Tweets to Improve Twitter Opinion Mining. in Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. vol. 2017-December, IEEE, pp. 965-970, 16th IEEE International Conference on Machine Learning and Applications (ICMLA), Cancun, Mexico, 18/12/17. https://doi.org/10.1109/ICMLA.2017.00-28

@inproceedings{b401c39c3c8f4193a1d3e65ae4a5ea68,

title = "Using Short URLs in Tweets to Improve Twitter Opinion Mining",

abstract = "Using short URLs in Twitter messages has increased in popularity in the past few years. This is mostly due to the fact that Twitter, as one of the most popular social media networks, imposes a 140 character limit to the messages distributed over the network. This paper analyzes the use of short URLs by Twitter users. Specifically, the goal is to examine the content pointed by the short URLs as well as the potential impact on the performance of sentiment analysis (opinion mining) tasks. Opinion mining based on Twitter feed has been used in an array of applications, including healthcare, identifying public opinion on political issues, financial modeling and advertising. Past research has however completely disregarded tweets which contain URLs. It is not hard to see how opinion mining can be improved considering the fact that Twitter users regularly post URLs pointing to articles endorsing a particular political figure, articles in important financial outlets or reviews of products. This study is based on the analysis of three distinct Twitter datasets with varying number of tweets which include short URLs. Popular machine learning techniques used in opinion mining were deployed in different experimental settings to conclude which are the most lucrative options. {\textcopyright} 2017 IEEE.",

author = "Andrei Pavel and Vasile Palade and Rahat Iqbal and Diana Hintea",

year = "2017",

month = dec,

doi = "10.1109/ICMLA.2017.00-28",

language = "English",

isbn = "978-153861417-4",

volume = "2017-December",

pages = "965--970",

booktitle = "Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017",

publisher = "IEEE",

address = "United States",

note = "16th IEEE International Conference on Machine Learning and Applications (ICMLA) ; Conference date: 18-12-2017 Through 21-12-2017",

url = "http://www.icmla-conference.org/icmla17/",

}

TY - GEN

T1 - Using Short URLs in Tweets to Improve Twitter Opinion Mining

AU - Pavel, Andrei

AU - Palade, Vasile

AU - Iqbal, Rahat

AU - Hintea, Diana

PY - 2017/12

Y1 - 2017/12

N2 - Using short URLs in Twitter messages has increased in popularity in the past few years. This is mostly due to the fact that Twitter, as one of the most popular social media networks, imposes a 140 character limit to the messages distributed over the network. This paper analyzes the use of short URLs by Twitter users. Specifically, the goal is to examine the content pointed by the short URLs as well as the potential impact on the performance of sentiment analysis (opinion mining) tasks. Opinion mining based on Twitter feed has been used in an array of applications, including healthcare, identifying public opinion on political issues, financial modeling and advertising. Past research has however completely disregarded tweets which contain URLs. It is not hard to see how opinion mining can be improved considering the fact that Twitter users regularly post URLs pointing to articles endorsing a particular political figure, articles in important financial outlets or reviews of products. This study is based on the analysis of three distinct Twitter datasets with varying number of tweets which include short URLs. Popular machine learning techniques used in opinion mining were deployed in different experimental settings to conclude which are the most lucrative options. © 2017 IEEE.

AB - Using short URLs in Twitter messages has increased in popularity in the past few years. This is mostly due to the fact that Twitter, as one of the most popular social media networks, imposes a 140 character limit to the messages distributed over the network. This paper analyzes the use of short URLs by Twitter users. Specifically, the goal is to examine the content pointed by the short URLs as well as the potential impact on the performance of sentiment analysis (opinion mining) tasks. Opinion mining based on Twitter feed has been used in an array of applications, including healthcare, identifying public opinion on political issues, financial modeling and advertising. Past research has however completely disregarded tweets which contain URLs. It is not hard to see how opinion mining can be improved considering the fact that Twitter users regularly post URLs pointing to articles endorsing a particular political figure, articles in important financial outlets or reviews of products. This study is based on the analysis of three distinct Twitter datasets with varying number of tweets which include short URLs. Popular machine learning techniques used in opinion mining were deployed in different experimental settings to conclude which are the most lucrative options. © 2017 IEEE.

U2 - 10.1109/ICMLA.2017.00-28

DO - 10.1109/ICMLA.2017.00-28

M3 - Conference proceeding

SN - 978-153861417-4

VL - 2017-December

SP - 965

EP - 970

BT - Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017

PB - IEEE

T2 - 16th IEEE International Conference on Machine Learning and Applications (ICMLA)

Y2 - 18 December 2017 through 21 December 2017

ER -

Using Short URLs in Tweets to Improve Twitter Opinion Mining

Abstract

Conference

Access to Document

Fingerprint

Cite this