Enhancement of Sentiment Analysis by Utilizing Noisy Social Media Texts 


Vol. 45,  No. 6, pp. 1027-1037, Jun.  2020
10.7840/kics.2020.45.6.1027


PDF
  Abstract

We proposed a new method to enhance sentiment analysis of social media text by utilizing the noisy text instead of filtering them out. The social media text contains numerous variations and inconsistencies due to the author"s limited vocabulary in a specific language, cognitive and typo spell-errors, abbreviating and shortening, and expression of emotions. Such variations result in generating lexically invalid words (misspelled words), which are considered as noise. Most of the existing work either filter out such noise or create a lexicon of these variations. The former method results in sentiment information loss while the latter method is highly application dependent. In this work, we propose a generic approach that can automatically handle the inconsistencies in the informal social media text. The proposed method conserves the sentiment information present in the noisy text by correcting the useful noisy terms rather than eliminating them. In the simulation, we integrated an ensembled sentiment analysis technique with an enhanced spell-checking technique for the correction of invalid words. The proposed scheme outperforms the state-of-the-art sentiment analysis schemes in terms of precision, recall, accuracy, and F1-score in simulation.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

J. Khan and S. Lee, "Enhancement of Sentiment Analysis by Utilizing Noisy Social Media Texts," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 6, pp. 1027-1037, 2020. DOI: 10.7840/kics.2020.45.6.1027.

[ACM Style]

Jebran Khan and Sungchang Lee. 2020. Enhancement of Sentiment Analysis by Utilizing Noisy Social Media Texts. The Journal of Korean Institute of Communications and Information Sciences, 45, 6, (2020), 1027-1037. DOI: 10.7840/kics.2020.45.6.1027.

[KICS Style]

Jebran Khan and Sungchang Lee, "Enhancement of Sentiment Analysis by Utilizing Noisy Social Media Texts," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 6, pp. 1027-1037, 6. 2020. (https://doi.org/10.7840/kics.2020.45.6.1027)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880