• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.4090-4102
• /
• 2018

After emerging online communications, text mining and sentiment analysis has been frequently applied into analyzing electronic word-of-mouth. This study aims to develop a domain-specific lexicon of sentiment analysis to predict box office success in Korea film market and validate the feasibility of the lexicon. Natural language processing, a machine learning algorithm, and a lexicon-based sentiment classification method are employed. To create a movie domain sentiment lexicon, 233,631 reviews of 147 movies with popularity ratings is collected by a XML crawling package in R program. We accomplished 81.69% accuracy in sentiment classification by the Korean sentiment dictionary including 706 negative words and 617 positive words. The result showed a stronger positive relationship with box office success and consumers' sentiment as well as a significant positive effect in the linear regression for the predicting model. In addition, it reveals emotion in the user-generated content can be a more accurate clue to predict business success.

• The Journal of Society for e-Business Studies
• /
• v.21 no.1
• /
• pp.65-77
• /
• 2016

As respecting one's privacy becomes an important issue in mobile device data analysis, on-device analysis is getting attention, in which the data analysis is conducted inside a mobile device without sending data from the device to outside. One possible application of the on-device analysis is gender prediction using text data in mobile devices, such as text messages, search keyword, website bookmarks, and contact, which are highly private, and the limited computing power of mobile devices can be addressed by utilizing the word comparison method, where words are selected beforehand and delivered to a mobile device of a user to determine the user's gender by matching mobile text data and the selected words. Moreover, it is known that performing prediction after filtering instances using definite evidences increases accuracy and reduces computational complexity. In this regard, we propose a two-phase approach to on-device gender prediction, where both discriminability and popularity of a word are sequentially considered. The proposed method performs predictions using a few highly discriminative words for all instances and popular words for unclassified instances from the previous prediction. From the experiments conducted on real-world dataset, the proposed method outperformed the compared methods.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.5
• /
• pp.733-739
• /
• 1987

In this paper, variable threshold detection with weighted pulse code modulation-encoded signals transmitted over Gaussian channels has been investigated. Each bit in the \ulcornerlaw PCM word is weighted according to its significance in the transmitter. It the output falls into the erasure zone, the regenerated sample replaced by interpolation or prediction. To overall system signal to noise ratio for BPSK/PCM speech signals of this technique has been found. When the input signal level was -17 db, the gains in overall signal s/n compared to weighted PCM and variable threshold detection were 5 db and 3 db, respectively. Computer simulation was performed generating signals by computer. The simulation was in resonable agreement with our theoretical prediction.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.613-616
• /
• 2018

Sequence tagging is an important task in Natural Language Processing (NLP), in which the Named Entity Recognition (NER) is the key issue. So far the most widely adopted model for NER in NLP is that of combining the neural network of bidirectional long short-term memory (BiLSTM) and the statistical sequence prediction method of Conditional Random Field (CRF). In this work, we improve the prediction accuracy of the BiLSTM by supporting an aligned word representation mechanism. We have performed experiments on multilingual (English, Spanish and Dutch) datasets and confirmed that our proposed model outperformed the existing state-of-the-art models.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.9
• /
• pp.229-236
• /
• 2016

In the past, crime prediction methods utilized previous records to accurately predict crime occurrences. Yet these crime prediction models had difficulty in updating immense data. To enhance the crime prediction methods, some approaches used social network service (SNS) data in crime prediction studies, but the relationship between SNS data and crime records has not been studied thoroughly. Hence, in this paper, we analyze the relationship between SNS data and criminal occurrences in the perspective of crime prediction. Using Latent Dirichlet Allocation (LDA), we extract tweets that included any words regarding criminal occurrences and analyze the changes in tweet frequency according to the crime records. We then calculate the number of tweets including crime related words and investigate accordingly depending on crime occurrences. Our experimental results demonstrate that there is a difference in crime related tweet occurrences when criminal activity occurs. Moreover, our results show that SNS data analysis will be helpful in crime prediction model as there are certain patterns in tweet occurrences before and after the crime.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.260-263
• /
• 2000

A technique that uses linear prediction to achieve noise reduction in a voice signal which has been mixed with an ambient noise (Signal to Noise (S-N) ratio = about 0dB) is proposed. This noise reduction method which is based on the linear prediction estimates the voice spectrum while ignoring the spectrum of the noise. The performance of the noise reduction method is first examined using the transversal linear predictor filter. However, with this method there is deterioration in the tone quality of the predicted voice due to the low level of the S-N ratio. An additional processing circuit is then proposed so as to adjust the noise reduction circuit with an aim of improving the problem of tone deterioration. Next, we consider a practical application where the effects of round on errors arising from fixed-point computation has to be minimized. This minimization is achieved by using the lattice predictor filter which in comparison to the transversal type, is Down to be less sensitive to the round-off error associated with finite word length operations. Finally, we consider a practical application where noise reduction is necessary. In this noise reduction method, both the voice spectrum and the actual noise spectrum are estimated. Noise reduction is achieved by using the linear predictor filter which includes the control of the predictor filter coefficient’s update.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1400-1418
• /
• 2020

In the development of commercial promotion, chatbot is known as one of significant skill by application of natural language processing (NLP). Conventional design methods are using bag-of-words model (BOW) alone based on Google database and other online corpus. For one thing, in the bag-of-words model, the vectors are Irrelevant to one another. Even though this method is friendly to discrete features, it is not conducive to the machine to understand continuous statements due to the loss of the connection between words in the encoded word vector. For other thing, existing methods are used to test in state-of-the-art online corpus but it is hard to apply in real applications such as telemarketing data. In this paper, we propose an improved chatbot design way using hybrid bag-of-words model and skip-gram model based on the real telemarketing data. Specifically, we first collect the real data in the telemarketing field and perform data cleaning and data classification on the constructed corpus. Second, the word representation is adopted hybrid bag-of-words model and skip-gram model. The skip-gram model maps synonyms in the vicinity of vector space. The correlation between words is expressed, so the amount of information contained in the word vector is increased, making up for the shortcomings caused by using bag-of-words model alone. Third, we use the term frequency-inverse document frequency (TF-IDF) weighting method to improve the weight of key words, then output the final word expression. At last, the answer is produced using hybrid retrieval model and generate model. The retrieval model can accurately answer questions in the field. The generate model can supplement the question of answering the open domain, in which the answer to the final reply is completed by long-short term memory (LSTM) training and prediction. Experimental results show which the hybrid word vector expression model can improve the accuracy of the response and the whole system can communicate with humans.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.870-878
• /
• 2019

In this paper, we propose an Attention-based BLSTM for predicting the video compression standard of a video. Recently, in NLP, many researches have been studied to predict the next word of sentences, classify and translate sentences by their semantics using the structure of RNN, and they were commercialized as chatbots, AI speakers and translator applications, etc. LSTM is designed to solve the gradient vanishing problem in RNN, and is used in NLP. The proposed algorithm makes video compression standard prediction possible by applying BLSTM and Attention algorithm which focuses on the most important word in a sentence to a bitstream of a video, not an sentence of a natural language.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.4
• /
• pp.103-110
• /
• 2019

A patent contains detailed information of the developed technology and is published to the public. Thus, patents can be used to overcome the limitations of traditional technology trend research and prediction techniques. Recently, due to the advantages of patented analytical methodology, IP R&D is carried out worldwide. The patent is big data and has a huge amount, various domains, and structured and unstructured data characteristics. For this reason, there are many difficulties in collecting and researching patent information. Patent research generally writes the Search formula to collect patent documents from DB. The collected patent documents contain some noise patents that are irrelevant to the purpose of analysis, so they are removed. However, eliminating noise patents is a manual task of reading and classifying technology, which is time consuming and expensive. In this study, we propose a model that automatically classifies The Noise patent for efficient patent information research. The proposed method performs Patent Embedding using Word2Vec and generates Noise seed label. In addition, noise patent classification is performed using the Random forest. The experimental data is published and registered with the USPTO among the patents related to Ocean Surveillance & Tracking Network technology. As a result of experimenting with the proposed model, it showed 73% accuracy with the label actually given by experts.