LSTM based Deep RNN Architecture for Election Sentiment Analysis from Bengali Newspaper

Saha, Baidya Nath; Senapati, Apurbalal; Mahajan, Anmol

doi:10.1109/compe49325.2020.9200062

Cited by 7 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bengali comments, text, etc., are quite unofficial data as far need much moderation [12]. Again, for classifying political news, problem will arise dealing with limited terms [13]. Comparing those, our proposed model works much efficiently as it deals with 10 categories, preprocessed data with 'GloVe', filter-based analogy using advanced features of LSTM.…”

Section: Resultsmentioning

confidence: 99%

Bangla News Classification Using GloVe Vectorization, LSTM, and CNN

Chowdhury

Eumi

Sarkar

et al. 2021

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

Text mining has gained considerable popularity over the last few years. Since the awareness of mobile media, streaming media, print media, and many other outlets are now accessible to consumers. Due to the large availability of text in many respects, research experts registered many unstructured data and found various ways in the literature of converting this dispersed text into a given, organized volume. Compared to the short text, the emphasis on complete classification (complete news, big records, long text, etc.) is prevalent. We addressed in this paper the process of text classification, grading, and various methodologies for feature extraction in short texts, i.e., news classification based on their headlines. Existing classification is compared and their operating methodologies presented efficiently. This work serves the purpose of classifying different types of Bangla Newspaper articles into 10 specific categories. The classification task is performed on Bengali text from three renowned newspapers of Kolkata. We have used advanced data tokenization techniques and unsupervised 'GloVe' vectorization for better classification performance. We applied LSTM and CNN as our main feature extractors. Comparing with other models like binary SVM classifier, standard LSTM, BiLSTM, CNN, or ANN, this proposed work gives better accuracy of 87%.

show abstract

Section: Resultsmentioning

confidence: 99%

Bangla News Classification Using GloVe Vectorization, LSTM, and CNN

Chowdhury

Eumi

Sarkar

et al. 2021

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

show abstract

“…RNN dapat menggunakan keadaan internal (memori) untuk memproses urutan input. Hal ini berlaku dalam (NLP) [15], pengenalan suara (speech recognition) [25], music synthesis [27], dan pemrosesan data keuangan [28]. Perhitungan RNN ditunjukkan pada Persamaan 2 dan Persamaan 3 dibawah ini.…”

Section: Tf-idfunclassified

“…Nilai recall dapat dihitung menggunakan Persamaan 7. [24] 82,48% Naïve Bayes [24] 76,56% Naive Bayes [25] 75,58% SVM [25] 63,99% KNN [25] 73,34% Naïve Bayes [26] 74,2% SVM [26] 81,2% Random Forest [26] 72,5% RNN [27] 91,9% RNN [28] 85% RNN [29] 95% Naïve Bayes (TF-IDF) 80% RNN (TF-IDF) 97,7%…”

Section: Performansimentioning

confidence: 99%

Analisis Sentimen Tweet Vaksin COVID-19 Menggunakan Recurrent Neural Network dan Naïve Bayes

Lestandy

Abdurrahim

Syafaah

2021

RESTI

View full text Add to dashboard Cite

COVID-19 has become a global pandemic including Indonesia, so the government is taking vaccinations as a preventive measure. The public's response to this continues to appear on social media platforms, one of which is Twitter. Tweets about the COVID-19 vaccine have generated various kinds of positive and negative opinions in the community. Therefore, it is very important to detect and filter it to prevent the spread of incorrect information. Sentiment analysis is a method used to determine the content of a dataset in the form of negative, positive or neutral text. The dataset in this study was obtained from 5000 COVID-19 vaccine tweets with the distribution of 3800 positive sentiment tweets, 800 negative sentiment tweets and 400 neutral sentiment tweets. The dataset obtained is then pre-processed data to optimize data processing. There are 4 stages of pre-processing, including remove punctuation, case folding, stemming and tokenizing. This study examines the performance of RNN and Naïve Bayes by adding the TF-IDF (Term Frequency-Inverse Document Frequency) technique which aims to give weight to the word relationship (term) of a document. The test results show that RNN (TF-IDF) has a greater accuracy of 97.77% compared to Naïve Bayes (TF-IDF) of 80%.

show abstract

“…Additionally, recurrent neural networks perform well for modeling time series. There have been many achievements in machine translation [37,38], sentiment analysis [39,40], stock prediction [41], and other fields. Significant temporal correlation of ship flooding fits with recurrent neural networks.…”

Section: Introductionmentioning

confidence: 99%

Ship Flooding Time Prediction Based on Composite Neural Network

Yang

Yin

2023

JMSE

View full text Add to dashboard Cite

When a ship sailing on the sea encounters flooding events, quickly predicting the flooding time of the compartments in the damaged area is beneficial to making evacuation decisions and reducing losses. At present, decision-makers obtain flooding data through various sensors arranged on board to predict the time of compartment flooding. These data help with the calculation of the flooding time in emergency situations. This paper proposes a new approach to obtaining the compartment flooding time. Specifically in damage scenarios, based on Convolutional Neural Network and Recurrent Neural Network (CNN-RNN), using a composite neural network framework estimates the time when the compartment’s flooding water reaches the target height. The input of the neural network is the flooding images of the damaged compartment. Transfer learning is utilized in the paper. The ResNet18 model in Pytorch is used to extract the spatial information from the flooding images. The Long Short-Term Memory (LSTM) model is then applied to predict when the compartment flooding water reaches the target height. Experimental results show that, for the damaged compartment, the flooding time predicted by the neural network is 85% accurate while the others’ accuracy is more than 91%. Intuitively, when it comes to the actual flooding event, the composite neural network’s average prediction error for compartment flooding time is approximately 1 min. To summarize, these results suggest that the composite neural network proposed above can provide flooding information to assist decision-makers in emergency situations.

show abstract

LSTM based Deep RNN Architecture for Election Sentiment Analysis from Bengali Newspaper

Cited by 7 publications

References 7 publications

Bangla News Classification Using GloVe Vectorization, LSTM, and CNN

Bangla News Classification Using GloVe Vectorization, LSTM, and CNN

Analisis Sentimen Tweet Vaksin COVID-19 Menggunakan Recurrent Neural Network dan Naïve Bayes

Ship Flooding Time Prediction Based on Composite Neural Network

Contact Info

Product

Resources

About