A Sentiment Analysis Dataset for Code-Mixed Malayalam-English

Bharathi Raja Chakravarthi; Navya Jose; Suryawanshi Suryawanshi; Elizabeth Sherly; John Philip McCrae

doi:10.13025/21374

A Sentiment Analysis Dataset for Code-Mixed Malayalam-English

Bharathi Raja Chakravarthi
, Navya Jose
, Suryawanshi Suryawanshi
, Elizabeth Sherly
, John Philip McCrae

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

Abstract

There is an increasing demand for sentiment analysis of text from social media which are mostly code-mixed. Systems trained on monolingual data fail for code-mixed data due to the complexity of mixing at different levels of the text. However, very few resources are available for code-mixed data to create models specific for this data. Although much research in multilingual and cross-lingual sentiment analysis has used semi-supervised or unsupervised methods, supervised methods still performs better. Only a few datasets for popular languages such as English-Spanish, English-Hindi, and English-Chinese are available. There are no resources available for Malayalam-English code-mixed data. This paper presents a new gold standard corpus for sentiment analysis of code-mixed text in Malayalam-English annotated by voluntary annotators. This gold standard corpus obtained a Krippendorff’s alpha above 0.8 for the dataset. We use this new corpus to provide the benchmark for sentiment analysis in Malayalam-English code-mixed texts

Original language	English (Ireland)
Title of host publication	Proceedings of 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop at LREC 2020
Publisher	European Language Resources Association (ELRA)
Number of pages	7
DOIs	https://doi.org/10.13025/21374
Publication status	Published - 1 Jan 2020

Access to Document

10.13025/21374Licence: CC BY-NC-ND

2020Accepted author manuscript, 283 KBLicence: CC BY-NC-ND

Cite this

Chakravarthi, B. R., Jose, N., Suryawanshi, S., Sherly, E., & McCrae, J. P. (2020). A Sentiment Analysis Dataset for Code-Mixed Malayalam-English. In Proceedings of 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop at LREC 2020 European Language Resources Association (ELRA). https://doi.org/10.13025/21374

Chakravarthi, Bharathi Raja ; Jose, Navya ; Suryawanshi, Suryawanshi et al. / A Sentiment Analysis Dataset for Code-Mixed Malayalam-English. Proceedings of 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop at LREC 2020. European Language Resources Association (ELRA), 2020.

@inproceedings{0d97998779044bfb8935d45867d4df20,

title = "A Sentiment Analysis Dataset for Code-Mixed Malayalam-English",

abstract = "There is an increasing demand for sentiment analysis of text from social media which are mostly code-mixed. Systems trained on monolingual data fail for code-mixed data due to the complexity of mixing at different levels of the text. However, very few resources are available for code-mixed data to create models specific for this data. Although much research in multilingual and cross-lingual sentiment analysis has used semi-supervised or unsupervised methods, supervised methods still performs better. Only a few datasets for popular languages such as English-Spanish, English-Hindi, and English-Chinese are available. There are no resources available for Malayalam-English code-mixed data. This paper presents a new gold standard corpus for sentiment analysis of code-mixed text in Malayalam-English annotated by voluntary annotators. This gold standard corpus obtained a Krippendorff{\textquoteright}s alpha above 0.8 for the dataset. We use this new corpus to provide the benchmark for sentiment analysis in Malayalam-English code-mixed texts",

author = "Chakravarthi, \{Bharathi Raja\} and Navya Jose and Suryawanshi Suryawanshi and Elizabeth Sherly and McCrae, \{John Philip\}",

year = "2020",

month = jan,

day = "1",

doi = "10.13025/21374",

language = "English (Ireland)",

booktitle = "Proceedings of 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop at LREC 2020",

publisher = "European Language Resources Association (ELRA)",

}

Chakravarthi, BR, Jose, N, Suryawanshi, S, Sherly, E & McCrae, JP 2020, A Sentiment Analysis Dataset for Code-Mixed Malayalam-English. in Proceedings of 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop at LREC 2020. European Language Resources Association (ELRA). https://doi.org/10.13025/21374

A Sentiment Analysis Dataset for Code-Mixed Malayalam-English. / Chakravarthi, Bharathi Raja; Jose, Navya; Suryawanshi, Suryawanshi et al.
Proceedings of 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop at LREC 2020. European Language Resources Association (ELRA), 2020.

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - A Sentiment Analysis Dataset for Code-Mixed Malayalam-English

AU - Chakravarthi, Bharathi Raja

AU - Jose, Navya

AU - Suryawanshi, Suryawanshi

AU - Sherly, Elizabeth

AU - McCrae, John Philip

PY - 2020/1/1

Y1 - 2020/1/1

N2 - There is an increasing demand for sentiment analysis of text from social media which are mostly code-mixed. Systems trained on monolingual data fail for code-mixed data due to the complexity of mixing at different levels of the text. However, very few resources are available for code-mixed data to create models specific for this data. Although much research in multilingual and cross-lingual sentiment analysis has used semi-supervised or unsupervised methods, supervised methods still performs better. Only a few datasets for popular languages such as English-Spanish, English-Hindi, and English-Chinese are available. There are no resources available for Malayalam-English code-mixed data. This paper presents a new gold standard corpus for sentiment analysis of code-mixed text in Malayalam-English annotated by voluntary annotators. This gold standard corpus obtained a Krippendorff’s alpha above 0.8 for the dataset. We use this new corpus to provide the benchmark for sentiment analysis in Malayalam-English code-mixed texts

AB - There is an increasing demand for sentiment analysis of text from social media which are mostly code-mixed. Systems trained on monolingual data fail for code-mixed data due to the complexity of mixing at different levels of the text. However, very few resources are available for code-mixed data to create models specific for this data. Although much research in multilingual and cross-lingual sentiment analysis has used semi-supervised or unsupervised methods, supervised methods still performs better. Only a few datasets for popular languages such as English-Spanish, English-Hindi, and English-Chinese are available. There are no resources available for Malayalam-English code-mixed data. This paper presents a new gold standard corpus for sentiment analysis of code-mixed text in Malayalam-English annotated by voluntary annotators. This gold standard corpus obtained a Krippendorff’s alpha above 0.8 for the dataset. We use this new corpus to provide the benchmark for sentiment analysis in Malayalam-English code-mixed texts

UR - http://hdl.handle.net/10379/16103

U2 - 10.13025/21374

DO - 10.13025/21374

M3 - Conference Publication

BT - Proceedings of 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop at LREC 2020

PB - European Language Resources Association (ELRA)

ER -

Chakravarthi BR, Jose N, Suryawanshi S, Sherly E, McCrae JP. A Sentiment Analysis Dataset for Code-Mixed Malayalam-English. In Proceedings of 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop at LREC 2020. European Language Resources Association (ELRA). 2020 doi: 10.13025/21374

A Sentiment Analysis Dataset for Code-Mixed Malayalam-English

Abstract

Access to Document

Other files and links

Fingerprint

Cite this