Thai sentiment analysis with deep learning techniques: A comparative study based on word embedding, POS-tag, and sentic features

Pasupa, Kitsuchart; Ayutthaya, Thititorn Seneewong Na

doi:10.1016/j.scs.2019.101615

Cited by 58 publications

(33 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LSTM method was introduced by Hochreiter and Schmidhuber [ 58 ] to overcome these challenges. LSTM cells are combined with the standard RNN method by replacing its hidden layer and playing the memory unit's role through gradient descent [ 57 , 59 , 60 ]. After that, it is trained using the backpropagation algorithm.…”

Section: Methodsmentioning

confidence: 99%

A Deep Learning Approach for Table Tennis Forehand Stroke Evaluation System Using an IMU Sensor

Tabrizi

Pashazadeh

Javani

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Psychological and behavioral evidence suggests that home sports activity reduces negative moods and anxiety during lockdown days of COVID-19. Low-cost, nonintrusive, and privacy-preserving smart virtual-coach Table Tennis training assistance could help to stay active and healthy at home. In this paper, a study was performed to develop a Forehand stroke’ performance evaluation system as the second principal component of the virtual-coach Table Tennis shadow-play training system. This study was conducted to show the effectiveness of the proposed LSTM model, compared with 2DCNN and RBF-SVR time-series analysis and machine learning methods, in evaluating the Table Tennis Forehand shadow-play sensory data provided by the authors. The data was generated, comprising 16 players’ Forehand strokes racket’s movement and orientation measurements; besides, the strokes’ evaluation scores were assigned by the three coaches. The authors investigated the ML models’ behaviors changed by the hyperparameters values. The experimental results of the weighted average of RMSE revealed that the modified LSTM models achieved 33.79% and 4.24% estimation error lower than 2DCNN and RBF-SVR, respectively. However, the R ¯ 2 results show that all nonlinear regression models are fit enough on the observed data. The modified LSTM is the most powerful regression method among all the three Forehand types in the current study.

show abstract

Section: Methodsmentioning

confidence: 99%

A Deep Learning Approach for Table Tennis Forehand Stroke Evaluation System Using an IMU Sensor

Tabrizi

Pashazadeh

Javani

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Gharibshah et al also used LSTM to create a deep learning framework, that could predict users' interest and display recommended advertisements, when they are browsing the website [14] . In addition, deep learning techniques have been used with various types of data other than clicking log data—e.g., face [15] , [16] , eye gaze [17] , gesture [18] , text [19] , [20] , [21] , [22] —to assist in understanding customers and improving customer satisfaction. However, a deep learning technique also requires a large labeled dataset to train a generalized model, but, again, collecting a large labeled dataset is expensive and laborious.…”

Section: Related Workmentioning

confidence: 99%

Identifying SME customers from click feedback on mobile banking apps: Supervised and semi-supervised approaches

Tungjitnob

Pasupa

Suntisrivaraporn

2021

Heliyon

Self Cite

View full text Add to dashboard Cite

Nowadays, the banking industry has moved from traditional branch services into mobile banking applications or apps. Using customer segmentation, banks can obtain more insights and better understand their customers' lifestyle and their behavior. In this work, we described a method to classify mobile app user click behavior into two groups, i.e. SME and Non-SME users. This task enabled the bank to identify anonymous users and offer them the right services and products. We extracted hand-crafted features from click log data and evaluated them with the Extreme Gradient Boosting algorithm (XGBoost). We also converted these logs into images, which captured temporal information. These image representations reduced the need for feature engineering, were easier to visualize and trained with a Convolutional Neural Network (CNN). We used ResNet-18 with the image dataset and achieved 71.69% accuracy on average, which outperformed XGBoost, which only achieved 61.70% accuracy. We also evaluated a semi-supervised learning model with our converted image data. Our semi-supervised method achieved 73.12% accuracy, using just half of the labeled images, combined with unlabeled images. Our method showed that these converted images were able to train with a semi-supervised algorithm that performed better than CNN with fewer labeled images. Our work also led to a better understanding of mobile banking user behavior and a novel way of developing a customer segmentation classifier.

show abstract

“…In 2019, Soumya using Malayalam tweets dataset with machine learning techniques to analyze the sentiment. The tweets are classified into positive and negativeusing Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF) [10]. Abyan collect data reviews of the body shop tea tree oil on Twitter with positive and negative sentiments and with the accuracy level of Tea Tree Oil sentiment analysis models on female daily at 61.51% [11].…”

Section: Related Workmentioning

confidence: 99%

Twitter Sentiment Analysis of Covid-19 Using Term Weighting TF-IDF And Logistic Regresion

Imamah

Rachman

2020

2020 6th Information Technology International Seminar (ITIS)

View full text Add to dashboard Cite

attack world population, and has brought much impact in all aspects of life. Stay at home and doing less in terms of social interactions. This can have a negative effect on mental health, so in this study we use sentiment analysis to know about mental health through public opinion on Twitter. Dataset which used in this study in this study is covid-19 tweets collected at 30 April 2020. Essentially, this dataset consists of 355384 tweets reviews. Covid-19 tweets will classify with the Logistic Regression method. Based on this research, the accuracy of the covid-19 tweeets sentiment classification is 94.71%.

show abstract

Thai sentiment analysis with deep learning techniques: A comparative study based on word embedding, POS-tag, and sentic features

Cited by 58 publications

References 25 publications

A Deep Learning Approach for Table Tennis Forehand Stroke Evaluation System Using an IMU Sensor

A Deep Learning Approach for Table Tennis Forehand Stroke Evaluation System Using an IMU Sensor

Identifying SME customers from click feedback on mobile banking apps: Supervised and semi-supervised approaches

Twitter Sentiment Analysis of Covid-19 Using Term Weighting TF-IDF And Logistic Regresion

Contact Info

Product

Resources

About