@inproceedings{batanovic-etal-2016-reliable,
title = "Reliable Baselines for Sentiment Analysis in Resource-Limited Languages: The {S}erbian Movie Review Dataset",
author = "Batanovi{\'c}, Vuk and
Nikoli{\'c}, Bo{\v{s}}ko and
Milosavljevi{\'c}, Milan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1427/",
pages = "2688--2696",
abstract = "Collecting data for sentiment analysis in resource-limited languages carries a significant risk of sample selection bias, since the small quantities of available data are most likely not representative of the whole population. Ignoring this bias leads to less robust machine learning classifiers and less reliable evaluation results. In this paper we present a dataset balancing algorithm that minimizes the sample selection bias by eliminating irrelevant systematic differences between the sentiment classes. We prove its superiority over the random sampling method and we use it to create the Serbian movie review dataset {\textemdash} SerbMR {\textemdash} the first balanced and topically uniform sentiment analysis dataset in Serbian. In addition, we propose an incremental way of finding the optimal combination of simple text processing options and machine learning features for sentiment classification. Several popular classifiers are used in conjunction with this evaluation approach in order to establish strong but reliable baselines for sentiment analysis in Serbian."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="batanovic-etal-2016-reliable">
<titleInfo>
<title>Reliable Baselines for Sentiment Analysis in Resource-Limited Languages: The Serbian Movie Review Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vuk</namePart>
<namePart type="family">Batanović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boško</namePart>
<namePart type="family">Nikolić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milan</namePart>
<namePart type="family">Milosavljević</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Collecting data for sentiment analysis in resource-limited languages carries a significant risk of sample selection bias, since the small quantities of available data are most likely not representative of the whole population. Ignoring this bias leads to less robust machine learning classifiers and less reliable evaluation results. In this paper we present a dataset balancing algorithm that minimizes the sample selection bias by eliminating irrelevant systematic differences between the sentiment classes. We prove its superiority over the random sampling method and we use it to create the Serbian movie review dataset — SerbMR — the first balanced and topically uniform sentiment analysis dataset in Serbian. In addition, we propose an incremental way of finding the optimal combination of simple text processing options and machine learning features for sentiment classification. Several popular classifiers are used in conjunction with this evaluation approach in order to establish strong but reliable baselines for sentiment analysis in Serbian.</abstract>
<identifier type="citekey">batanovic-etal-2016-reliable</identifier>
<location>
<url>https://aclanthology.org/L16-1427/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2688</start>
<end>2696</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reliable Baselines for Sentiment Analysis in Resource-Limited Languages: The Serbian Movie Review Dataset
%A Batanović, Vuk
%A Nikolić, Boško
%A Milosavljević, Milan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F batanovic-etal-2016-reliable
%X Collecting data for sentiment analysis in resource-limited languages carries a significant risk of sample selection bias, since the small quantities of available data are most likely not representative of the whole population. Ignoring this bias leads to less robust machine learning classifiers and less reliable evaluation results. In this paper we present a dataset balancing algorithm that minimizes the sample selection bias by eliminating irrelevant systematic differences between the sentiment classes. We prove its superiority over the random sampling method and we use it to create the Serbian movie review dataset — SerbMR — the first balanced and topically uniform sentiment analysis dataset in Serbian. In addition, we propose an incremental way of finding the optimal combination of simple text processing options and machine learning features for sentiment classification. Several popular classifiers are used in conjunction with this evaluation approach in order to establish strong but reliable baselines for sentiment analysis in Serbian.
%U https://aclanthology.org/L16-1427/
%P 2688-2696
Markdown (Informal)
[Reliable Baselines for Sentiment Analysis in Resource-Limited Languages: The Serbian Movie Review Dataset](https://aclanthology.org/L16-1427/) (Batanović et al., LREC 2016)
ACL