Sentiment Analysis on Roman Urdu Students’ Feedback Using Enhanced Word Embedding Technique
Students’ feedback is crucial for educational institutions to assess the performance of their teachers, most opinions are expressed in their native language, especially for people in south Asian regions. In Pakistan, people use Roman Urdu to express their reviews, and this applied in the educat...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
College of Science for Women, University of Baghdad
2024-02-01
|
| Series: | Baghdad Science Journal |
| Subjects: | |
| Online Access: | https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/9822 |
| _version_ | 1827339192138465280 |
|---|---|
| author | Noureen Sharin Hazlin Huspi Huspi Zafar Ali |
| author_facet | Noureen Sharin Hazlin Huspi Huspi Zafar Ali |
| author_sort | Noureen |
| collection | DOAJ |
| description |
Students’ feedback is crucial for educational institutions to assess the performance of their teachers, most opinions are expressed in their native language, especially for people in south Asian regions. In Pakistan, people use Roman Urdu to express their reviews, and this applied in the education domain where students used Roman Urdu to express their feedback. It is very time-consuming and labor-intensive process to handle qualitative opinions manually. Additionally, it can be difficult to determine sentence semantics in a text that is written in a colloquial style like Roman Urdu. This study proposes an enhanced word embedding technique and investigates the neural word Embedding (Word2Vec and Glove) to determine which performs better for Roman Urdu Sentiment analysis. Our suggested model employs the BiLSTM network to maintain the context in both directions and eventually, results for ternary classification are obtained by using the final softmax output layer. A manually labeled data set was used to evaluate the model, data is collected from the HEIs of Pakistan. Model was empirically evaluated on two datasets of Roman Urdu, the newly developed student’s feedback dataset and RUSA-19 publically available data set of Roman Urdu. Our model performs effectively using the word embedding and BiLSTM layer. The proposed model is compared with the baseline models of CNN, RNN, GRU and classic LSTM. The experimental findings demonstrate the proposed model's efficacy with an F1score of 90%.
|
| first_indexed | 2024-03-07T19:47:45Z |
| format | Article |
| id | doaj.art-d275a841a607441984770e87747bad3c |
| institution | Directory Open Access Journal |
| issn | 2078-8665 2411-7986 |
| language | Arabic |
| last_indexed | 2024-03-07T19:47:45Z |
| publishDate | 2024-02-01 |
| publisher | College of Science for Women, University of Baghdad |
| record_format | Article |
| series | Baghdad Science Journal |
| spelling | doaj.art-d275a841a607441984770e87747bad3c2024-02-28T20:06:23ZaraCollege of Science for Women, University of BaghdadBaghdad Science Journal2078-86652411-79862024-02-01212(SI)10.21123/bsj.2024.9822Sentiment Analysis on Roman Urdu Students’ Feedback Using Enhanced Word Embedding TechniqueNoureen0Sharin Hazlin Huspi Huspi 1Zafar Ali 2Department of Applied Computing and Artificial Intelligence, Universiti Teknologi Malaysia, Johor, Malaysia.Department of Applied Computing and Artificial Intelligence, Universiti Teknologi Malaysia, Johor, Malaysia.Razak Faculty of Technology and Informatics, Universiti Teknologi Malaysia, Kuala Lumpur, Malaysia.&Department of Computer Science, Sukkur IBA University, Sukkur 65200, Pakistan. Students’ feedback is crucial for educational institutions to assess the performance of their teachers, most opinions are expressed in their native language, especially for people in south Asian regions. In Pakistan, people use Roman Urdu to express their reviews, and this applied in the education domain where students used Roman Urdu to express their feedback. It is very time-consuming and labor-intensive process to handle qualitative opinions manually. Additionally, it can be difficult to determine sentence semantics in a text that is written in a colloquial style like Roman Urdu. This study proposes an enhanced word embedding technique and investigates the neural word Embedding (Word2Vec and Glove) to determine which performs better for Roman Urdu Sentiment analysis. Our suggested model employs the BiLSTM network to maintain the context in both directions and eventually, results for ternary classification are obtained by using the final softmax output layer. A manually labeled data set was used to evaluate the model, data is collected from the HEIs of Pakistan. Model was empirically evaluated on two datasets of Roman Urdu, the newly developed student’s feedback dataset and RUSA-19 publically available data set of Roman Urdu. Our model performs effectively using the word embedding and BiLSTM layer. The proposed model is compared with the baseline models of CNN, RNN, GRU and classic LSTM. The experimental findings demonstrate the proposed model's efficacy with an F1score of 90%. https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/9822Long Short-term memory network, Roman Urdu, Sentiment Analysis, Student feedback, Word Embedding |
| spellingShingle | Noureen Sharin Hazlin Huspi Huspi Zafar Ali Sentiment Analysis on Roman Urdu Students’ Feedback Using Enhanced Word Embedding Technique Baghdad Science Journal Long Short-term memory network, Roman Urdu, Sentiment Analysis, Student feedback, Word Embedding |
| title | Sentiment Analysis on Roman Urdu Students’ Feedback Using Enhanced Word Embedding Technique |
| title_full | Sentiment Analysis on Roman Urdu Students’ Feedback Using Enhanced Word Embedding Technique |
| title_fullStr | Sentiment Analysis on Roman Urdu Students’ Feedback Using Enhanced Word Embedding Technique |
| title_full_unstemmed | Sentiment Analysis on Roman Urdu Students’ Feedback Using Enhanced Word Embedding Technique |
| title_short | Sentiment Analysis on Roman Urdu Students’ Feedback Using Enhanced Word Embedding Technique |
| title_sort | sentiment analysis on roman urdu students feedback using enhanced word embedding technique |
| topic | Long Short-term memory network, Roman Urdu, Sentiment Analysis, Student feedback, Word Embedding |
| url | https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/9822 |
| work_keys_str_mv | AT noureen sentimentanalysisonromanurdustudentsfeedbackusingenhancedwordembeddingtechnique AT sharinhazlinhuspihuspi sentimentanalysisonromanurdustudentsfeedbackusingenhancedwordembeddingtechnique AT zafarali sentimentanalysisonromanurdustudentsfeedbackusingenhancedwordembeddingtechnique |