What is it about?
This article discusses a model that handles the transliteration problems using phonetic Levenstein distance and also uses the syllable level and word level embeddings to find the sentiment of the given sentence.
Featured Image
Photo by Towfiqu barbhuiya on Unsplash
Why is it important?
Multilingual societies and advancements in communication technologies had accounted for the prolific usage of mixed data, which rendered the state-of-art sentiment analysis models developed based on monolingual data ineffective. Social media usersin the Indian sub-continent exhibited a tendency to mix English and their respective native language (using the phonetic form of English) in expressing their opinions or sentiments.
Perspectives
Syllable-level features are very important for languages that have mixed with the English language. Here, the user has the flexibility to express the native language words with utterances in Roman script.
Mr Upendar Rao Rayala
National Institute of Technology Andhra Pradesh and Rajiv Gandhi University of Knowledge Technologies Nuzvid
Read the Original
This page is a summary of: Sentiment analysis of code-mixed Telugu-English data leveraging syllable and word embeddings, ACM Transactions on Asian and Low-Resource Language Information Processing, September 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3620670.
You can read the full text:
Resources
Contributors
The following have contributed to this page
