Sentiment Analysis of Movie Review Using Integrated CNN-LSTM Mode (CNN-LSTM 조합모델을 이용한 영화리뷰 감성분석)
-
- Journal of Intelligence and Information Systems
- /
- v.25 no.4
- /
- pp.141-154
- /
- 2019
Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.
In the field of dentistry, there existed relatively few emergency patients or patients who need intensive care and thus had low medical dispute rates. However, these days, there is a general tendency of increased medical disputes. Although many medical disputes are caused by medical accidents of the dentists, because dental assistants are also lawfully involved in practicing dentistry, there is a possibility of medical disputes or medical accidents caused by dental assistants. Therefore, the role of the dental assistants cannot be ignored. This study consists of a survey given to dental hygienists currently working in general hospitals, dental hospitals and private dental clinics. Following is the results of the analysis of 275 respondents' backgrounds, medical disputes rates including patients' complaints, their understanding of medical regulations and their general understanding of overall dental practice and medical disputes. 1. 251 of 274(91.6%) respondents doubted the risk of medical accident and dispute. 2. 81(29.5%) dental hygienist experienced complaint from patients. They have been working in the private dental clinic, the rate of this experience was high. 3. 349 case of 1805(19.3%) the complaints by patients, highest percentage among its category, were those regarding dental fees and poor service. 4. 129 case of 1805(7.1%) patients' complaints, highest percentage among it's subcategory, were those regarding the absence of explanations of precautions or request of agreements before dental treatment. 5. 252 of 267 (94.4%) dental hygienists chart after a scaling treatment. However, only 55(20.7%) dental hygienists chart the fact of explaining the precautions. 6. 6(2.2%) dental hygienists do not inspect patients' medical history, if patients don't mention it. 7. 104 of 274(38.0%) dental hygienists responded to be capable of administering first aid treatment. 8. 115(41.8%) dental hygienists have a first aid kit and equipment. 9. In case of medical dispute, 268(97.8%) dental hygienists respond that, charting plays a big role in resolving the dispute. 10. In case of medical dispute, 272(93.3%) dental hygienists respond that, explanation and agreement before treatment have an important role in settlement of dispute 11. Only 160(58.4%) dental hygienists responded correct answer that the duration of keeping medical records is 10 years. 12. 124(45.3%) respondents thought that it is legal for a dental hygienist to take a panoramic dental X-ray, 71(25.9%) respondents thought that it is legal practice cervical resin treatment by dental hygienist, and 37(13.5%) respondents thought that it is legal extract primary teeth by dental hygienist. 13. 24(18.76%) respondents thought that it doesn't matter to tell patient's state to others 14. 272(99.27%) responded that receiving education for the prevention of medical disputes was needed and of them, 61.0% thought it was urgent. 15. 186(64.2%) has never had classes regarding the prevention of medical disputes while in school and 212(77.4%) has not had the same type of classes after graduating from school. 16. 256(93.4%) responded that there will be even more of an increased number of medical disputes. Among them, 83.3% of respondents though that due to the increased opportunity of acquiring information through the internet and mass media. The study shows that 29.5 percentage of dental hygienists have experienced the medical disputes and complaints and they are lack of recognition of medical regulations and dental hygienist's official duty. So, there is a big potential of the percentage to increase. Therefore, the correct understanding of explaining precautions and requesting agreement before dental treatments and performing them are mandatory. Moreover, classes regarding the prevention and counterplans of medical disputes need to be widely offered.