Geodesic
SMS Sentiment Classification based on Lexical Features, Emoticons and Informal Abbreviations
Serdica Journal of Computing, Tome 13 (2019) no. 1-2, pp. 081-096.

Voir la notice de l'article provenant de la source Bulgarian Digital Mathematics Library

In this paper we investigate the influence of emoticons, informal speech, lexical and other linguistic features on the sentiment contained in SMS messages. Using the dataset of ∼ 6,000 samples, we trained a linear SVM classifier able to determine positive, negative and neutral sentiments. The dataset mostly contains messages in Serbian, but also in English and German. The classifier had an average accuracy score of 92.3% in a 5-fold Cross Validation setting, and F1-score of 92.1%, 74.0% and 93.3% in favor of the positive, negative and neutral class, respectively.
Keywords: Computer Application in Arts and Humanities, Web-Based Services, Document Analysis 
@article{SJC_2019_13_1-2_a5,
     author = {\v{S}andrih, Branislava},
     title = {SMS {Sentiment} {Classification} based on {Lexical} {Features,} {Emoticons} and {Informal} {Abbreviations}},
     journal = {Serdica Journal of Computing},
     pages = {081--096},
     publisher = {mathdoc},
     volume = {13},
     number = {1-2},
     year = {2019},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/SJC_2019_13_1-2_a5/}
}
TY  - JOUR
AU  - Šandrih, Branislava
TI  - SMS Sentiment Classification based on Lexical Features, Emoticons and Informal Abbreviations
JO  - Serdica Journal of Computing
PY  - 2019
SP  - 081
EP  - 096
VL  - 13
IS  - 1-2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/SJC_2019_13_1-2_a5/
LA  - en
ID  - SJC_2019_13_1-2_a5
ER  - 
%0 Journal Article
%A Šandrih, Branislava
%T SMS Sentiment Classification based on Lexical Features, Emoticons and Informal Abbreviations
%J Serdica Journal of Computing
%D 2019
%P 081-096
%V 13
%N 1-2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/SJC_2019_13_1-2_a5/
%G en
%F SJC_2019_13_1-2_a5
Šandrih, Branislava. SMS Sentiment Classification based on Lexical Features, Emoticons and Informal Abbreviations. Serdica Journal of Computing, Tome 13 (2019) no. 1-2, pp. 081-096. http://geodesic.mathdoc.fr/item/SJC_2019_13_1-2_a5/