@inproceedings{stankovic-etal-2022-sentiment,
title = "Sentiment Analysis of {S}erbian Old Novels",
author = "Stankovi{\'c}, Ranka and
Ko{\v{s}}prdi{\'c}, Milo{\v{s}} and
Ikoni{\'c} Ne{\v{s}}i{\'c}, Milica and
Radovi{\'c}, Tijana",
editor = "Kernerman, Ilan and
Carvalho, Sara and
Iglesias, Carlos A. and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 2nd Workshop on Sentiment Analysis and Linguistic Linked Data",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.salld-1.6",
pages = "31--38",
abstract = "In this paper we present first study of Sentiment Analysis (SA) of Serbian novels from the 1840-1920 period. The preparation of sentiment lexicon was based on three existing lexicons: \textit{NRC}, \textit{AFFIN} and \textit{Bing} with additional extensive corrections. The first phase of dataset refinement included filtering the word that are not found in Serbian morphological dictionary and in second automatic POS tagging and lemma were manually corrected. The polarity lexicon was extracted and transformed into \textit{ontolex-lemon} and published as initial version. The complex inflection system of Serbian language required expansion of sentiment lexicon with inflected forms from Serbian morphological dictionaries. Set of sentences for SA was extracted from 120 novels of Serbian part of ELTeC collection, labelled for polarity and used for several model training. Several approaches for SA are compared, starting with for variation of lexicon based and followed by Logistic Regression, Naive Bayes, Decision Tree, Random Forest, SVN and k-NN. The comparison with models trained on labelled movie reviews dataset indicates that it can not successfully be used for sentiment analysis of sentences in old novels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stankovic-etal-2022-sentiment">
<titleInfo>
<title>Sentiment Analysis of Serbian Old Novels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ranka</namePart>
<namePart type="family">Stanković</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miloš</namePart>
<namePart type="family">Košprdić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Ikonić Nešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tijana</namePart>
<namePart type="family">Radović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Sentiment Analysis and Linguistic Linked Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilan</namePart>
<namePart type="family">Kernerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Carvalho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Iglesias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present first study of Sentiment Analysis (SA) of Serbian novels from the 1840-1920 period. The preparation of sentiment lexicon was based on three existing lexicons: NRC, AFFIN and Bing with additional extensive corrections. The first phase of dataset refinement included filtering the word that are not found in Serbian morphological dictionary and in second automatic POS tagging and lemma were manually corrected. The polarity lexicon was extracted and transformed into ontolex-lemon and published as initial version. The complex inflection system of Serbian language required expansion of sentiment lexicon with inflected forms from Serbian morphological dictionaries. Set of sentences for SA was extracted from 120 novels of Serbian part of ELTeC collection, labelled for polarity and used for several model training. Several approaches for SA are compared, starting with for variation of lexicon based and followed by Logistic Regression, Naive Bayes, Decision Tree, Random Forest, SVN and k-NN. The comparison with models trained on labelled movie reviews dataset indicates that it can not successfully be used for sentiment analysis of sentences in old novels.</abstract>
<identifier type="citekey">stankovic-etal-2022-sentiment</identifier>
<location>
<url>https://aclanthology.org/2022.salld-1.6</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>31</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentiment Analysis of Serbian Old Novels
%A Stanković, Ranka
%A Košprdić, Miloš
%A Ikonić Nešić, Milica
%A Radović, Tijana
%Y Kernerman, Ilan
%Y Carvalho, Sara
%Y Iglesias, Carlos A.
%Y Sprugnoli, Rachele
%S Proceedings of the 2nd Workshop on Sentiment Analysis and Linguistic Linked Data
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F stankovic-etal-2022-sentiment
%X In this paper we present first study of Sentiment Analysis (SA) of Serbian novels from the 1840-1920 period. The preparation of sentiment lexicon was based on three existing lexicons: NRC, AFFIN and Bing with additional extensive corrections. The first phase of dataset refinement included filtering the word that are not found in Serbian morphological dictionary and in second automatic POS tagging and lemma were manually corrected. The polarity lexicon was extracted and transformed into ontolex-lemon and published as initial version. The complex inflection system of Serbian language required expansion of sentiment lexicon with inflected forms from Serbian morphological dictionaries. Set of sentences for SA was extracted from 120 novels of Serbian part of ELTeC collection, labelled for polarity and used for several model training. Several approaches for SA are compared, starting with for variation of lexicon based and followed by Logistic Regression, Naive Bayes, Decision Tree, Random Forest, SVN and k-NN. The comparison with models trained on labelled movie reviews dataset indicates that it can not successfully be used for sentiment analysis of sentences in old novels.
%U https://aclanthology.org/2022.salld-1.6
%P 31-38
Markdown (Informal)
[Sentiment Analysis of Serbian Old Novels](https://aclanthology.org/2022.salld-1.6) (Stanković et al., SALLD 2022)
ACL
- Ranka Stanković, Miloš Košprdić, Milica Ikonić Nešić, and Tijana Radović. 2022. Sentiment Analysis of Serbian Old Novels. In Proceedings of the 2nd Workshop on Sentiment Analysis and Linguistic Linked Data, pages 31–38, Marseille, France. European Language Resources Association.