Code-mixed Data Research Articles

Abusive Comment Detection in Tamil Code-Mixed Data by Adjusting Class Weights and Refining Features

In recent years, a significant portion of the content on various platforms on the internet has been found to be offensive or abusive. Abusive comment detection can go a long way in preventing internet users from facing the adverse effects of coming in contact with abusive language. This problem is particularly challenging when the comments are found in low-resource languages like Tamil or Tamil-English code-mixed text. So far, there has not been any substantial work on abusive comment detection using imbalanced datasets. Furthermore, significant work has not been performed, especially for Tamil code-mixed data, that involves analysing the dataset for classification and accordingly creating a custom vocabulary for preprocessing. This paper proposes a novel approach to classify abusive comments from an imbalanced dataset using a customised training vocabulary and a combination of statistical feature selection with language-agnostic feature selection while making use of explainable AI for feature refinement. Our model achieved an accuracy of 74% and a macro F1-score of 0.46.

Share What You Already Know: Cross-Language-Script Transfer and Alignment for Sentiment Detection in Code-Mixed Data

Code-switching entails mixing multiple languages. It is an increasingly occurring phenomenon in social media texts. Usually, code-mixed texts are written in a single script, even though the languages involved have different scripts. Pre-trained multilingual models primarily utilize the data in the native script of the language. In existing studies, the code-switched texts are utilized as they are. However, using the native script for each language can generate better representations of the text owing to the pre-trained knowledge. Therefore, a cross-language-script knowledge sharing architecture utilizing the cross attention and alignment of the representations of text in individual language scripts was proposed in this study. Experimental results on two different datasets containing Nepali-English and Hindi-English code-switched texts, demonstrate the effectiveness of the proposed method. The interpretation of the model using model explainability technique illustrates the sharing of language-specific knowledge between language-specific representations.

Consensus-Based Machine Translation for Code-Mixed Texts

Multilingualism in India is widespread due to its long history of foreign acquaintances. This leads to the presence of an audience familiar with conversing using more than one language. Additionally, due to the social media boom, the usage of multiple languages to communicate has become extensive. Hence, the need for a translation system that can serve the novice and monolingual user is the need of the hour. Such translation systems can be developed by methods such as statistical machine translation and neural machine translation, where each approach has its advantages as well as disadvantages. In addition, the parallel corpus needed to build a translation system, with code-mixed data, is not readily available. In the present work, we present two translation frameworks that can leverage the individual advantages of these pre-existing approaches by building an ensemble model that takes a consensus of the final outputs of the preceding approaches and generates the target output. The developed models were used for translating English-Bengali code-mixed data (written in Roman script) into their equivalent monolingual Bengali instances. A code-mixed to monolingual parallel corpus was also developed to train the preceding systems. Empirical results show improved BLEU and TER scores of 17.23 and 53.18 and 19.12 and 51.29, respectively, for the developed frameworks.

Transformer Based Sentiment Analysis on Code Mixed Data

In India, a country known for its linguistic diversity, code mixing is a common practice, and it has a profound impact on the way people communicate through various mediums, including social media platforms and everyday conversations. The prevalence of code-mixing in social media platforms presents a substantial hurdle for machine translation and language processing tasks. The abundance of unstructured text in code-mixed form on these platforms highlights a crucial research domain within NLP. The blending of Hindi and English, known as Hinglish, and other mixed case text like Malayalam-English, Tamil-English, Telugu- English are particularly prevalent among the younger generation while communication in social media and requires appropriate processing to aid comprehension by both monolingual users and language processing models. Manual translation of this type of data proves to be laborious due to challenges like limited vocabulary, potential misunderstandings of context, grammatical errors, biases, and various other issues. Additionally, existing translation models tend to perform more effectively on monolingual language rather than code-mixed data. Therefore, it is more desirable to build models that can translate code-mixed data.This study tries to convert code-mixed Hinglish, Malayalam-English, Tamil-English, Telugu-English language in Romanised script to monolingual English which can further be given as input to NLP applications like Sentiment Analysis. This is achieved by finetuning pretrained models like IndicLID for Language Identification (LID) module and use an ensemble approach for transliteration + translation using Indictrans and IndicXlit for code mixed machine translation which will be given as input to classification algorithm which performs Sentiment Analysis and predict the sentiment. It is observed that this approach of translation of code-mixed test perform better than traditional machine translation for Indian languages Hindi, Tamil, Telugu and Malayalam.

Transformer based model for offensive content recognition in dravidian languages

This paper describes a model for spotting offensive data from the comments being collected from social media. The comments posted will include expressions, emoticons and will mostly be in code mixed language and classifying these code-mixed language comments is tricky. The proposed system uses a multi-head attention model to extract features from the code-mixed Tamil input data. Various classification algorithms are applied to these extracted features to categorize offensive comments. The generated labels are optimized by performing majority voting on labels generated by different algorithms. This system is validated on the validation set and is evaluated by applying the Tamil CodeMix test data from the dataset published by the HASOC task (Task2-subtask1) at FIRE 2021. The evaluation yields an average weighted F1 score of 0.83 and is ranked 3rd position in the official ranking.

Language augmentation approach for code-mixed text classification

The usage of more than one language in the same text is referred to as Code Mixed. It is evident that there is a growing degree of adaption of the use of code-mixed data, especially English with a regional language, on social media platforms. Existing deep-learning models do not take advantage of the implicit language information in the code-mixed text. Our study aims to improve BERT-based models’ performance on low-resource Code-Mixed Hindi–English Datasets by experimenting with language augmentation approaches. For language augmentation in BERT models, we explore word-level interleaving and post-sentence placement of language information. We have examined the performance of vanilla BERT-based models and their code-mixed HingBERT counterparts on respective benchmark datasets, comparing their results with and without using word-level language information. The models were evaluated using metrics such as accuracy, precision, recall, and F1 score. Our findings show that the proposed language augmentation approaches work well across different BERT models. We demonstrate the importance of augmenting code-mixed text with language information on five different code-mixed Hindi–English classification datasets based on sentiment analysis, hate speech detection, and emotion detection.

Sentiment Analysis of Code-Mixed Telugu-English Data Leveraging Syllable and Word Embeddings

Learning the inherent meaning of a word in Natural Language Processing (NLP) has motivated researchers to represent a word at various levels of abstraction, namely character-level, morpheme-level, and subword-level vector representations. Syllable-Aware Word Embedding (SAWE) can effectively handle agglutinative and fusion-based NLP tasks. However, research attempts on assessing the SAWE on such extrinsic NLP tasks has been scanty, especially for low-resource languages in the context of code-mixing with English. A model to learn SAWE to extract semantics at fine-grained subunits of a word is proposed in this article, and the representative ability of the embeddings is assessed through sentiment analysis of code-mixed Telugu-English review corpora. Multilingual societies and advancements in communication technologies have accounted for the prolific usage of mixed data, which renders the State-of-the-Art (SOTA) sentiment analysis models developed based on monolingual data ineffective. Social media users in the Indian subcontinent exhibit a tendency to mix English and their respective native language (using the phonetic form of English) in expressing their opinions or sentiments. A code-mixing scenario provides flexibility to borrow words from a foreign language, usage of shorthand notations, elongation of vowels, and usage of words without following syntactic/grammatical rules, which renders the sentiment analysis of code-mixed data challenging to perform. Deep neural architectures like Long Short-Term Memory and Gated Recurrent Unit networks have been shown to be effective in solving several NLP tasks, such as sequence labeling, named entity recognition, and machine translation. In this article, a framework to perform sentiment analysis on a code-mixed Telugu-English review corpus is implemented. Both word embedding and SAWE are input to a unified deep neural network that contains a two-level Bidirectional Long Short-Term Memory/Gated Recurrent Unit network with Softmax as the output layer. The proposed model leverages the advantages of both word embedding and SAWE, which enable the proposed model to outperform existing SOTA code-mixed sentiment analysis models on a Telugu-English code-mixed dataset of the International Institute of Information Technology–Hyderabad and a dataset curated by the authors. The improvement realized by the proposed model on these datasets is [3% increase in F1-score and 2% increase in accuracy] and [7% increase in F1-score and 5% in accuracy], respectively, in comparison with the best-performing SOTA model.

ALIH KODE DAN CAMPUR KODE PADA DIALOG ANTARTOKOH FILM BUMI MANUSIA KARYA HANUNG BRAMANTYO

This study aims to describe the forms of code-switching and code-mixing as well as the causal factors found in the film Earth of Mankind by Hanung Bramantyo. This research is a qualitative descriptive study using a sociolinguistic approach. The data collection technique used in this study is the observing and noting technique. The subject of this study is the film Bumi Manusia by Hanung Bramantyo. Based on the research that has been done, there are forms of code switching and code mixing as well as the causative factors that occur in the dialogue between the characters in the film Bumi Manusia by Hanung Bramantyo. The results of this study obtained 49 data, namely 11 code switching data and 38 code mixing data. In this case, there are several languages used, including Indonesian, English, Dutch, French and Javanese.

The Effect of Stopword Removal on Information Retrieval for Code-Mixed Data Obtained Via Social Media

The Effect of Stopword Removal on Information Retrieval for Code-Mixed Data Obtained Via Social Media

Sentiment analysis based offensive language identification system for code-mixed data

Hate speech identification is the process of categorising textual information into hate and non- hate speech with the goal of identifying hate speech's targeted features. The objective of this research work is to take the Dataset from FIRE 2021 shared task code mixed data that includes YouTube comments and Twitter conversations and to detect whether the messages represents the offensive or non-offensive category. To detect the offensive language sentences, various deep learning models like Long Short-Term Memory, Bidirectional Long Short-Term Memory, Convolutional Neural Network, Gated Recurrent Unit, and hybrid model like Convolutional Neural Network with Bidirectional Long Short-Term Memory methods were utilised in this research work. The performance of all the mentioned models is evaluated using precision, recall, F1-score, and accuracy. Out of all the models, both LSTM and GRU models perform better with the accuracy of 0.81, precision of 0.85 and recall of 0.95.

A Framework for Online Hate Speech Detection on Code-mixed Hindi-English Text and Hindi Text in Devanagari

Social Media has been growing and has provided the world with a platform to opine, debate, display, and discuss like never before. It has a major influence in research areas that analyze human behavior and social groups, and the phenomenon of social interactions is even being used in areas such as Internet of Things. This constant stream of data connecting individuals and organizations across the globe has had a tremendous impact on the functioning of society and even has the power to sway elections. Despite having numerous benefits, social media has certain issues such as the prevalence of fake news, which has also led to the rise of the hate speech phenomenon. Due to lax security throughout these social media platforms, these issues continue to exist without any repercussions. This leads to cyberbullying, defamation, and presents grave security concerns. Even though some work has been done independently on native scripts, hate speech detection, and code-mixed data, there exists a lack of academic work and research in the area of detecting hate speech in transliterated code-mixed data and in-text containing native language scripts. Research in this field is inhibited greatly due to the multiple variations in grammar and spelling and in general a lack of availability of annotated datasets, especially when it comes to native languages. This article comes up with a method to automate hate speech detection in code-mixed and native language text. The article presents an architecture containing a Tabnet classifier-based model trained on features extracted using MuRIL from transliterated code-mixed textual data. The article also shows that the same model works well on features extracted from text in Devanagari despite being trained on transliterated data.

Campur Kode dalam Proses Pembelajaran di Sekolah Dasar Negeri 12 Padang Laweh Kabupaten Sijunjung

Abstract: Code Mixing in the Learning Process at Padang Laweh 12 Public Elementary School, Sijunjung Regency. The purpose of this study is to describe the forms and factors that cause code mixing in the learning process at Padang Laweh 12 Public Elementary School, Sijunjung Regency. This type of research is qualitative research. The research method uses descriptive method. The data in this study are words, phrases, clauses in the learning process at Padang Laweh 12 Public Elementary School, Sijunjung Regency. The sources in this study are audio and video recordings in the process. The results of the research that has been done, found 86 code mixing data in the learning process at Padang Laweh 12 Public Elementary School, Sijunjung Regency. Of the 86 data found, there were 35 mixed code words such as no, okay, uwang, kecek, rest, reminded, ado, there, etc., 32 mixed code phrases such as alhamdulillah, allhu akbar, what did you check mom earlier?, bakpo wak , cubo baco, and others, and 18 code mixing clauses such as ha kambiongmelompek pageg jie serli, how come you can't wak kluag de, and others. In this study, there is also code mixing based on its nature, namely internal (internal) code mixing such as Indonesian to Minangkabau and vice versa and external (external) code mixing such as Indonesian to Arabic and vice versa. The causes of code-mixing are the speaker or speaker's personal factors, function and purpose factors, and the factor of arousing a sense of humor with jokes (funny impression).

Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch

Using off-the-shelf resources from resource-rich languages to transfer knowledge to low-resource languages has received a lot of attention. The requirements of enabling the model to achieve the reliable performance, including the scale of required annotated data and the effective framework, are not well guided. To address the first question, we empirically investigate the cost-effectiveness of several methods for training intent classification and slot-filling models from scratch in Indonesia (ID) using English data. Confronting the second challenge, we propose a Bi-Confidence-Frequency Cross-Lingual transfer framework (BiCF), which consists of “BiCF Mixing”, “Latent Space Refinement” and “Joint Decoder”, respectively, to overcome the lack of low-resource language dialogue data. BiCF Mixing based on the word-level alignment strategy generates code-mixed data by utilizing the importance-frequency and translating-confidence. Moreover, Latent Space Refinement trains a new dialogue understanding model using code-mixed data and word embedding models. Joint Decoder based on Bidirectional LSTM (BiLSTM) and Conditional Random Field (CRF) is used to obtain experimental results of intent classification and slot-filling. We also release a large-scale fine-labeled Indonesia dialogue dataset (ID-WOZ 1 ) and ID-BERT for experiments. BiCF achieves 93.56% and 85.17% (F1 score) on intent classification and slot filling, respectively. Extensive experiments demonstrate that our framework performs reliably and cost-efficiently on different scales of manually annotated Indonesian data.

THE USE OF CODE-MIXING IN INSTAGRAM CAPTIONS FROM THE STUDENTS OF ENGLISH LITERATURE STUDY PROGRAM, UNIVERSITAS RESPATI YOGYAKARTA: A SOCIOLINGUISTIC STUDY

This research discusses the code mixing used in the Instagram caption by students English Literature Study Program at Universitas Respati Yogyakarta. This research aims to find the types of code mixing used in Instagram captions and to understand the factors using code mixing in captions. The focus analysis of this research is by analyzing the context. This research was conducted by implementing a descriptive qualitative method in discussing code-mixing. A simple quantitative method is implemented to assist the qualitative method in explaining the data in the form of numbers or percentages. The findings of this research show that there are 70 code-mixing data found in Instagram captions. The analysis findings show that there are three types of code mixing found in Instagram captions. Those are code-mixing insertion, alternation and congruent lexicalization. From the results of the analysis in this research, the type of insertion is the type that is the highest or most commonly found, that is 54 data (59.1%). Then alternation type with 12 data (17.1%), and congruent lexicalization type with 4 data (5.71%). and for the results of the second question in this research, there are 60 data (85.71%) for the first factor talking about a particular topic, the second factor is being emphatic about something with 4 data (5.71%), the third factor is repetition used for clarification with 4 data (5.71%) and 2 data (4, 28) for the expressing group identity.

Analysis of Code Mixing on Media Social Shopee

The purpose of this study is to identify and describe external code mixing, internal code mixing and mixed code mixing on shopee social media. This study uses the theory of Sayama Malabar, Chaer and Agustina, Padmadewi et al, Nababan and Suardi. The method used in this study is a qualitative method using an analysis of the use of code mixing on shopee social media. The data analysis technique is used by learning about code mixing on Shopee's social media, studying the words found on Shopee's social media, concluding the results of the analysis. This research instrument is used to record code mixing on shopee social media. The results of this study obtained 50 code-mixed data, there were mixed code inside 5 with all 10 words, outside code mixed 40 with all words 840, and mixed code mixed 5 with all 91 words.

Deep learning based sentiment analysis and offensive language identification on multilingual code-mixed data

Sentiment analysis is a process in Natural Language Processing that involves detecting and classifying emotions in texts. The emotion is focused on a specific thing, an object, an incident, or an individual. Although some tasks are concerned with detecting the existence of emotion in text, others are concerned with finding the polarities of the text, which is classified as positive, negative, or neutral. The task of determining whether a comment contains inappropriate text that affects either individual or group is called offensive language identification. The existing research has concentrated more on sentiment analysis and offensive language identification in a monolingual data set than code-mixed data. Code-mixed data is framed by combining words and phrases from two or more distinct languages in a single text. It is quite challenging to identify emotion or offensive terms in the comments since noise exists in code-mixed data. The majority of advancements in hostile language detection and sentiment analysis are made on monolingual data for languages with high resource requirements. The proposed system attempts to perform both sentiment analysis and offensive language identification for low resource code-mixed data in Tamil and English using machine learning, deep learning and pre-trained models like BERT, RoBERTa and adapter-BERT. The dataset utilized for this research work is taken from a shared task on Multi task learning DravidianLangTech@ACL2022. Another challenge addressed by this work is the extraction of semantically meaningful information from code-mixed data using word embedding. The result represents an adapter-BERT model gives a better accuracy of 65% for sentiment analysis and 79% for offensive language identification when compared with other trained models.

Multitasking of sentiment detection and emotion recognition in code-mixed Hinglish data

As the number of non-native English speakers on social media has skyrocketed in recent years, sentiment and emotion analysis on regional languages and code-mixed data has gained traction. Despite extensive research on English, the area of Hindi–English code-mixed texts is still relatively new and understudied. We create an emotion annotated Hindi–English (Hinglish) code-mixed dataset by performing emotion annotation on the benchmark SentiMix dataset to solve this problem and enable future researchers to contribute to this domain. We propose an end-to-end transformer-based multitask framework for sentiment detection and emotion recognition from the SentiMix code-mixed dataset. We fine-tune the pre-trained cross-lingual embedding model, XLMR, using task-specific data to further exploit the efficacy of transfer learning to improve the overall efficiency of our methods. Our proposed multi-task solution outperforms the state-of-the-art single-task and multitask baselines by a considerable margin, implying that the auxiliary task (i.e. emotion recognition) increases the efficiency of the primary task (i.e. sentiment detection) in a multi-task environment. It should be noted that the reported findings were obtained without the use of any ensemble techniques, thereby adhering to a model of effective and production-ready NLP.

ANALYSIS OF CODE-SWITCHING AND CODE-MIXING USED IN RINTIK SEDU YOUTUBE CHANNEL’S VIDEO

<span lang="EN-GB">Rintik Sedu is an Indonesian writer's YouTube channel named Nadhifa Allya Tsana. As the content creator, Tsana masters Indonesian English and studies Korean self-taught. The mastery of the language causes code-mixing and code-switching found in Rintik Sedu YouTube channel’s videos. The study aimed to 1) identify the existing code-switching and code-mixing in Rintik Sedu YouTube channel’s video entitled </span><em><span lang="EN-GB">“it means you’re growing”</span></em><span lang="EN-GB">, 2) analyze the types of existing code-switching and code-mixing, and 3) describe the reason of code-switching and code-mixing used. The study used descriptive content analysis, which involved one of Rintik Sedu’s videos as a material to analyze. Some methods followed to collect the data, including searching the video, selecting and downloading the video, watching the video, transcribing the video’s audio, identifying the code-switching and code-mixing, and re-checking. The result found in this study are 1) Sixteen Indonesian Language-English code-switching data and fifteen Indonesian language-English code-mixing data. 2) The type of code-switching and code-mixing identified in Rintik Sedu’s video is external code-switching and outer code-mixing. 3) There are eight reasons for code-switching and code-mixing used.</span>

Traceback and Chunk-Based Learning: Comparing Usage-Based Computational Approaches to Child Code-Mixing

Recent years have seen increased interest in code-mixing from a usage-based perspective. In usage-based approaches to monolingual language acquisition, a number of methods have been developed that allow for detecting patterns from usage data. In this paper, we evaluate two of those methods with regard to their performance when applied to code-mixing data: the traceback method, as well as the chunk-based learner model. Both methods make it possible to automatically detect patterns in speech data. In doing so, however, they place different theoretical emphases: while traceback focuses on frame-and-slot patterns, chunk-based learner focuses on chunking processes. Both methods are applied to the code-mixing of a German–English bilingual child between the ages of 2;3 and 3;11. Advantages and disadvantages of both methods will be discussed, and the results will be interpreted against the background of usage-based approaches.

Alih Kode Dan Campur Kode Dalam Video Blogger Suki Suka Japan

This research is entitled "Code-switching and code-mixing in the video blogger Suki Suka Japan". The purpose of this research is to represent the factors that cause and types of the process of code-switching and code-mixing on the video blogger Suki Suka Japan. This study uses three theories, namely the theory of code-switching (Wardhaugh); code-mixing theory (Hoffmann), and the theory that causes code-mixing (Weinrich). The research method is discriptive analysis with an approach using listening techniques and note-taking techniques. Data were analyzed using agih and tapping methods as well as informal. The results showed that there were 3 types of metaphorical code-switching data and two types of situational code-switching data. In the code-mixing data, there are 2 pieces (code-mixing in sentences), 3 pieces (mixing code in lexical), and 1 pieces (mixing code in phonological).