Analysis of hyperparameters in Sentiment Analysis of Movie Reviews using Bi-LSTM
Movie reviews are an important factor in determining a film’s success because instead of depending solely on the number of views as a parameter for the success of the movie, movie reviews are used to acquire additional insights into the movie. Existing systems use LSTM for sentiment analysis but the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2022-01-01
|
| Series: | ITM Web of Conferences |
| Subjects: | |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2022/04/itmconf_icacc2022_03012.pdf |
| _version_ | 1818202888990621696 |
|---|---|
| author | Singh Amankumar Thapliyal Riya Vanave Ritika Shedge Rajashree Mumbaikar Snehal |
| author_facet | Singh Amankumar Thapliyal Riya Vanave Ritika Shedge Rajashree Mumbaikar Snehal |
| author_sort | Singh Amankumar |
| collection | DOAJ |
| description | Movie reviews are an important factor in determining a film’s success because instead of depending solely on the number of views as a parameter for the success of the movie, movie reviews are used to acquire additional insights into the movie. Existing systems use LSTM for sentiment analysis but there is no study available how various hyperparameters affect the performance of the model. Bi-LSTM along with dropout layers provide good accuracy in sentiment analysis. The suggested method outperforms CNN and Natural Language Toolkit in terms of accuracy.The proposed model is tested using different hyper parameters including dropout rate,number of Bi-LSTM layers and Bi-LSTM nodes. 64 LSTM nodes, 2 Bi-directional Layers, and a 0.2 Dropout rate should be used for optimal accuracy. Effect of different text vectorization algorithms and activation functions was also studied. The combination of Tf-idf text vectorization and the ReLU activation function yields the best results. |
| first_indexed | 2024-12-12T03:16:37Z |
| format | Article |
| id | doaj.art-467a817b9f8b48caaeb08689e97c6462 |
| institution | Directory Open Access Journal |
| issn | 2271-2097 |
| language | English |
| last_indexed | 2024-12-12T03:16:37Z |
| publishDate | 2022-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj.art-467a817b9f8b48caaeb08689e97c64622022-12-22T00:40:17ZengEDP SciencesITM Web of Conferences2271-20972022-01-01440301210.1051/itmconf/20224403012itmconf_icacc2022_03012Analysis of hyperparameters in Sentiment Analysis of Movie Reviews using Bi-LSTMSingh Amankumar0Thapliyal Riya1Vanave Ritika2Shedge Rajashree3Mumbaikar Snehal4Computer Engineering Department, Ramrao Adik Institute of TechnologyComputer Engineering Department, Ramrao Adik Institute of TechnologyComputer Engineering Department, Ramrao Adik Institute of TechnologyComputer Engineering Department, Ramrao Adik Institute of TechnologyComputer Engineering Department, Ramrao Adik Institute of TechnologyMovie reviews are an important factor in determining a film’s success because instead of depending solely on the number of views as a parameter for the success of the movie, movie reviews are used to acquire additional insights into the movie. Existing systems use LSTM for sentiment analysis but there is no study available how various hyperparameters affect the performance of the model. Bi-LSTM along with dropout layers provide good accuracy in sentiment analysis. The suggested method outperforms CNN and Natural Language Toolkit in terms of accuracy.The proposed model is tested using different hyper parameters including dropout rate,number of Bi-LSTM layers and Bi-LSTM nodes. 64 LSTM nodes, 2 Bi-directional Layers, and a 0.2 Dropout rate should be used for optimal accuracy. Effect of different text vectorization algorithms and activation functions was also studied. The combination of Tf-idf text vectorization and the ReLU activation function yields the best results.https://www.itm-conferences.org/articles/itmconf/pdf/2022/04/itmconf_icacc2022_03012.pdfsentiment analysistext-vectorizationbi-lstm |
| spellingShingle | Singh Amankumar Thapliyal Riya Vanave Ritika Shedge Rajashree Mumbaikar Snehal Analysis of hyperparameters in Sentiment Analysis of Movie Reviews using Bi-LSTM ITM Web of Conferences sentiment analysis text-vectorization bi-lstm |
| title | Analysis of hyperparameters in Sentiment Analysis of Movie Reviews using Bi-LSTM |
| title_full | Analysis of hyperparameters in Sentiment Analysis of Movie Reviews using Bi-LSTM |
| title_fullStr | Analysis of hyperparameters in Sentiment Analysis of Movie Reviews using Bi-LSTM |
| title_full_unstemmed | Analysis of hyperparameters in Sentiment Analysis of Movie Reviews using Bi-LSTM |
| title_short | Analysis of hyperparameters in Sentiment Analysis of Movie Reviews using Bi-LSTM |
| title_sort | analysis of hyperparameters in sentiment analysis of movie reviews using bi lstm |
| topic | sentiment analysis text-vectorization bi-lstm |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2022/04/itmconf_icacc2022_03012.pdf |
| work_keys_str_mv | AT singhamankumar analysisofhyperparametersinsentimentanalysisofmoviereviewsusingbilstm AT thapliyalriya analysisofhyperparametersinsentimentanalysisofmoviereviewsusingbilstm AT vanaveritika analysisofhyperparametersinsentimentanalysisofmoviereviewsusingbilstm AT shedgerajashree analysisofhyperparametersinsentimentanalysisofmoviereviewsusingbilstm AT mumbaikarsnehal analysisofhyperparametersinsentimentanalysisofmoviereviewsusingbilstm |