Home > Research > Publications & Outputs > Sentiment analysis tools should take account of...

Research

Associated organisational units

Electronic data

  • iiWAS2015_TEH_PHOEY_LEE_V2_scott

    Accepted author manuscript, 399 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Text available via DOI:

Keywords

View graph of relations

Sentiment analysis tools should take account of the number of exclamation marks!!!

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Sentiment analysis tools should take account of the number of exclamation marks!!! / Teh, Phoey Lee; Rayson, Paul Edward; Pak, Irina et al.
iiWAS '15 Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services. New York: ACM, 2015. 35.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Teh, PL, Rayson, PE, Pak, I & Piao, SS 2015, Sentiment analysis tools should take account of the number of exclamation marks!!! in iiWAS '15 Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services., 35, ACM, New York, The 17th International Conference on Information Integration and Web-based Applications & Services (iiWAS2015), Brussels, Belgium, 11/12/15. https://doi.org/10.1145/2837185.2837216

APA

Teh, P. L., Rayson, P. E., Pak, I., & Piao, S. S. (2015). Sentiment analysis tools should take account of the number of exclamation marks!!! In iiWAS '15 Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services Article 35 ACM. https://doi.org/10.1145/2837185.2837216

Vancouver

Teh PL, Rayson PE, Pak I, Piao SS. Sentiment analysis tools should take account of the number of exclamation marks!!! In iiWAS '15 Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services. New York: ACM. 2015. 35 doi: 10.1145/2837185.2837216

Author

Teh, Phoey Lee ; Rayson, Paul Edward ; Pak, Irina et al. / Sentiment analysis tools should take account of the number of exclamation marks!!!. iiWAS '15 Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services. New York : ACM, 2015.

Bibtex

@inproceedings{e780558ffcc2460888c6f2b102415ce1,
title = "Sentiment analysis tools should take account of the number of exclamation marks!!!",
abstract = "There are various factors that affect the sentiment level expressed in textual comments. Capitalization of letters tends to mark something for attention and repeating of letters tends to strengthen the emotion. Emoticons are used to help visualize facial expressions which can affect understanding of text. In this paper, we show the effect of the number of exclamation marks used, via testing with twelve online sentiment tools. We present opinions gathered from 500 respondents towards “like” and “dislike” values, with a varying number of exclamation marks. Results show that only 20% of the online sentiment tools tested considered the number of exclamation marks in their returned scores. However, results from our human raters show that themore exclamation marks used for positive comments, the more they have higher “like” values than the same comments with fewer exclamations marks. Similarly, adding more exclamation marksfor negative comments, results in a higher “dislike”.",
keywords = "Sentiment Analysis, LANGUAGES, Human factors",
author = "Teh, {Phoey Lee} and Rayson, {Paul Edward} and Irina Pak and Piao, {Scott Songlin}",
year = "2015",
month = dec,
day = "11",
doi = "10.1145/2837185.2837216",
language = "English",
isbn = "9781450334914",
booktitle = "iiWAS '15 Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services",
publisher = "ACM",
note = " The 17th International Conference on Information Integration and Web-based Applications & Services (iiWAS2015) ; Conference date: 11-12-2015 Through 13-12-2015",

}

RIS

TY - GEN

T1 - Sentiment analysis tools should take account of the number of exclamation marks!!!

AU - Teh, Phoey Lee

AU - Rayson, Paul Edward

AU - Pak, Irina

AU - Piao, Scott Songlin

PY - 2015/12/11

Y1 - 2015/12/11

N2 - There are various factors that affect the sentiment level expressed in textual comments. Capitalization of letters tends to mark something for attention and repeating of letters tends to strengthen the emotion. Emoticons are used to help visualize facial expressions which can affect understanding of text. In this paper, we show the effect of the number of exclamation marks used, via testing with twelve online sentiment tools. We present opinions gathered from 500 respondents towards “like” and “dislike” values, with a varying number of exclamation marks. Results show that only 20% of the online sentiment tools tested considered the number of exclamation marks in their returned scores. However, results from our human raters show that themore exclamation marks used for positive comments, the more they have higher “like” values than the same comments with fewer exclamations marks. Similarly, adding more exclamation marksfor negative comments, results in a higher “dislike”.

AB - There are various factors that affect the sentiment level expressed in textual comments. Capitalization of letters tends to mark something for attention and repeating of letters tends to strengthen the emotion. Emoticons are used to help visualize facial expressions which can affect understanding of text. In this paper, we show the effect of the number of exclamation marks used, via testing with twelve online sentiment tools. We present opinions gathered from 500 respondents towards “like” and “dislike” values, with a varying number of exclamation marks. Results show that only 20% of the online sentiment tools tested considered the number of exclamation marks in their returned scores. However, results from our human raters show that themore exclamation marks used for positive comments, the more they have higher “like” values than the same comments with fewer exclamations marks. Similarly, adding more exclamation marksfor negative comments, results in a higher “dislike”.

KW - Sentiment Analysis

KW - LANGUAGES

KW - Human factors

UR - http://www.iiwas.org/conferences/iiwas2015/home

U2 - 10.1145/2837185.2837216

DO - 10.1145/2837185.2837216

M3 - Conference contribution/Paper

SN - 9781450334914

BT - iiWAS '15 Proceedings of the 17th International Conference on Information Integration and Web-based Applications & Services

PB - ACM

CY - New York

T2 - The 17th International Conference on Information Integration and Web-based Applications & Services (iiWAS2015)

Y2 - 11 December 2015 through 13 December 2015

ER -