• Spatial Information Research
• /
• v.20 no.5
• /
• pp.99-109
• /
• 2012

Recently, due to the growth of social media and spread of smart-phone, the amount of data has considerably increased by full use of SNS (Social Network Service). According to it, the Big Data concept is come up and many researchers are seeking solutions to make the best use of big data. To maximize the creative value of the big data held by many companies, it is required to combine them with existing data. The physical and theoretical storage structures of data sources are so different that a system which can integrate and manage them is needed. In order to process big data, MapReduce is developed as a system which has advantages over processing data fast by distributed processing. However, it is difficult to construct and store a system for all key words. Due to the process of storage and search, it is to some extent difficult to do real-time processing. And it makes extra expenses to process complex event without structure of processing different data. In order to solve this problem, the existing Complex Event Processing System is supposed to be used. When it comes to complex event processing system, it gets data from different sources and combines them with each other to make it possible to do complex event processing that is useful for real-time processing specially in stream data. Nevertheless, unstructured data based on text of SNS and internet articles is managed as text type and there is a need to compare strings every time the query processing should be done. And it results in poor performance. Therefore, we try to make it possible to manage unstructured data and do query process fast in complex event processing system. And we extend the data complex function for giving theoretical schema of string. It is completed by changing the string key word into integer type with filtering which uses keyword set. In addition, by using the Complex Event Processing System and processing stream data at real-time of in-memory, we try to reduce the time of reading the query processing after it is stored in the disk.

• Asia pacific journal of information systems
• /
• v.23 no.2
• /
• pp.1-20
• /
• 2013

Social commerce has been gaining explosive popularity, with typical examples of the model such as Groupon and Level Up. Both local business owners and consumers can benefit from this new e-commerce model. Local business owners have a chance to access potential customers and promote their products in a way that could not have otherwise been easily possible, and consumers can enjoy discounted offerings. However, questions have been increasingly raised about the value and future of the social commerce model. A recent survey shows that about a third of 324 business owners who ran a daily-deal promotion in Groupon went behind. Furthermore, more than half of the surveyed merchants did not express enthusiasm about running the promotion again. The same goes for the case in Korea, where more than half of the surveyed clients reported no significant change or even decrease in profits compared to before the use of social commerce model. Why do local business owners fail to exploit the benefits from the promotions and advertisements through the social commerce model and to make profits? Without answering this question, the model would fall under suspicion and even its sustainability might be challenged. This study aims to look into problems in the current social commerce transactions and provide implications for the social commerce model, so that the model would get a foothold for next growth. Drawing on justice theory, this study develops theoretical arguments for the effects of transaction characteristics on consumers' distributive justice and purchase intention in the social commerce. Specifically, this study focuses on two characteristics of social commerce transactions-the discount rate and the purchase rate of products-and investigates their effects on consumers' perception of distributive justice for discounted transactions in the social commerce and their perception of distributive justice for regular-priced transactions. This study also examines the relationship between distributive justice and purchase intention. We conducted an online experiment and gathered data from 115 participants to test the hypotheses. Each participant was randomly assigned to one of nine manipulated scenarios of social commerce transactions, which were generated based on the combination of three levels of purchase rate (high, medium, and low) and three levels of discount rate (high, medium, and low). We conducted MANOVA and post-hoc ANOVA to test hypotheses about the relationships between the transaction characteristics (purchase rate and discount rate) and distributive justice for each of the discounted transaction and the regular-priced transaction. We also employed a PLS analysis to test relations between distributive justice and purchase intentions. Analysis results show that a higher discount rate increases distributive justice for the discounted transaction but decreases distributive justice for the regular-priced transaction. This, coupled with the result that distributive justice for each type of transaction has a positive effect on the corresponding purchase intention, implies that a large discount in the social commerce may be helpful for attracting consumers, but harmful to the business after the promotion. However, further examination reveals curvilinear effects of the discount rate on both types of distributive justice. Specifically, we find distributive justice for the discounted transaction increases concavely as the discount rate increases while distributive justice for the regular-priced transaction decreases concavely with the dscount rate. This implies that there exists an appropriate discount rate which could promote the discounted transaction while not hurting future business of regular-priced transactions. Next, the purchase rate is found to be a critical factor that facilitates the regular-priced transaction. It has a convexly positive influence on distributive justice for the transaction. Therefore, an increase of the rate beyond some threshold would lead to a substantial level of distributive justice for the regular-priced transaction, threrby boosting future transactions. This implies that social commerce firms and sellers should employ various non-price stimuli to promote the purchase rate. Finally, we find no significant relationship between the purchase rate and distributive justice for the discounted transaction. Based on the above results, we provide several implications with future research directions.

• Asia pacific journal of information systems
• /
• v.23 no.4
• /
• pp.1-28
• /
• 2013

Given that smartphone-based social network services (SNS), such as KakaoStory is now being widely used as a way for people to connect and communicate with each other, this study examines key factors leading to the continued use of SNS. People have been using PC-based SNS, such as Cyworld, for years are now using smartphone-based SNS, such as KakaoStory. KakaoStory developed by KakaoTalk has rapidly grown up as the largest smartphone-based SNS in Korea as smartphone penetration increases. It is more difficult for firms to maintain their current users over time in that alternative SNSs satisfying people's new needs are constantly emerging and evolving. In this sense, one of the most challenging issues for SNS firms is how to retain their current users in the long run. However, there are few empirical studies on this issue. Applying the IS continuance model proposed by Bhattacherjee [2001], this study explores key determinants of users' smartphone-based SNS continuance intention. The model suggests that perceived usefulness and user satisfaction are the key determinants of IS continuance intention. However, the model includes only the utilitarian value that users can obtain through the use of smartphone-based SNS, by considering perceived usefulness. Therefore, the study attempts to extend the IS continuance model by considering hedonic and social values simultaneously. More specifically, we consider subjective norms as social value that are proposed by the theory of reasoned action and the theory of planned behavior. We also consider perceived enjoyment as hedonic value that is emphasized as a key factor influencing users' behavior intention and actual behavior, particularly in the context of hedonic IS use. By considering the three values in our model simultaneously, we could offer a deeper understanding of smartphone-based SNS continuance. That is, this study could offer an explanation of how each value is associated with user satisfaction and SNS continuance intention. The customer value-satisfaction-loyalty model can strengthen the assertion that smartphone-based SNS continuance intention is determined by various different types of customer values, such as utilitarian, hedonic, and social ones. Moreover, the model provides a theoretical basis for the assertion that customer values lead to increased loyalty via customer satisfaction. In this regard, we theorize that SNS continuance intention is influenced by users' various values, namely perceived usefulness, perceived enjoyment, and subjective norms, via user satisfaction. To test the proposed research model and hypotheses, we conducted a partial least squares analysis using a total of 253 data collected on the users of smartphone-based SNS (i.e., KakaoStory). The key findings are as follows: First, it has been found that SNS continuance intention considerably depends on user satisfaction. Second, user satisfaction is determined by confirmation, perceived usefulness, and perceived enjoyment. Third, concerning the effects of the three values on SNS continuance intention, only perceived enjoyment regarded as hedonic value was statistically significant. That is, perceived usefulness considered as utilitarian value and subjective norms considered as social value had no effect on SNS continuance intention. Finally, our results indicate that confirmation increases perceived usefulness, perceived enjoyment, and user satisfaction. The results reconfirm the effectiveness of IS continuance model in predicting smartphone-based SNS continuance intention. Moreover, the results demonstrate that perceived enjoyment reflecting hedonic value is the most important predictor of SNS continuance intention. Therefore, it is imperative for firms to meet SNS users' hedonic value to retain them in the long run. Meanwhile, we could not find any empirical evidence to support the assertion that subjective norms are associated with user satisfaction and SNS continuance intention. The results lead us to conclude that when users have enough direct experience in SNS use, subjective norms have no effect on SNS continuance intention. Discussions and implications of the results are provided.

• 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 Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.101-124
• /
• 2018

Recently, most of the technologies have been developed in various forms through the advancement of single technology or interaction with other technologies. Particularly, these technologies have the characteristic of the convergence caused by the interaction between two or more techniques. In addition, efforts in responding to technological changes by advance are continuously increasing through forecasting promising convergence technologies that will emerge in the near future. According to this phenomenon, many researchers are attempting to perform various analyses about forecasting promising convergence technologies. A convergence technology has characteristics of various technologies according to the principle of generation. Therefore, forecasting promising convergence technologies is much more difficult than forecasting general technologies with high growth potential. Nevertheless, some achievements have been confirmed in an attempt to forecasting promising technologies using big data analysis and social network analysis. Studies of convergence technology through data analysis are actively conducted with the theme of discovering new convergence technologies and analyzing their trends. According that, information about new convergence technologies is being provided more abundantly than in the past. However, existing methods in analyzing convergence technology have some limitations. Firstly, most studies deal with convergence technology analyze data through predefined technology classifications. The technologies appearing recently tend to have characteristics of convergence and thus consist of technologies from various fields. In other words, the new convergence technologies may not belong to the defined classification. Therefore, the existing method does not properly reflect the dynamic change of the convergence phenomenon. Secondly, in order to forecast the promising convergence technologies, most of the existing analysis method use the general purpose indicators in process. This method does not fully utilize the specificity of convergence phenomenon. The new convergence technology is highly dependent on the existing technology, which is the origin of that technology. Based on that, it can grow into the independent field or disappear rapidly, according to the change of the dependent technology. In the existing analysis, the potential growth of convergence technology is judged through the traditional indicators designed from the general purpose. However, these indicators do not reflect the principle of convergence. In other words, these indicators do not reflect the characteristics of convergence technology, which brings the meaning of new technologies emerge through two or more mature technologies and grown technologies affect the creation of another technology. Thirdly, previous studies do not provide objective methods for evaluating the accuracy of models in forecasting promising convergence technologies. In the studies of convergence technology, the subject of forecasting promising technologies was relatively insufficient due to the complexity of the field. Therefore, it is difficult to find a method to evaluate the accuracy of the model that forecasting promising convergence technologies. In order to activate the field of forecasting promising convergence technology, it is important to establish a method for objectively verifying and evaluating the accuracy of the model proposed by each study. To overcome these limitations, we propose a new method for analysis of convergence technologies. First of all, through topic modeling, we derive a new technology classification in terms of text content. It reflects the dynamic change of the actual technology market, not the existing fixed classification standard. In addition, we identify the influence relationships between technologies through the topic correspondence weights of each document, and structuralize them into a network. In addition, we devise a centrality indicator (PGC, potential growth centrality) to forecast the future growth of technology by utilizing the centrality information of each technology. It reflects the convergence characteristics of each technology, according to technology maturity and interdependence between technologies. Along with this, we propose a method to evaluate the accuracy of forecasting model by measuring the growth rate of promising technology. It is based on the variation of potential growth centrality by period. In this paper, we conduct experiments with 13,477 patent documents dealing with technical contents to evaluate the performance and practical applicability of the proposed method. As a result, it is confirmed that the forecast model based on a centrality indicator of the proposed method has a maximum forecast accuracy of about 2.88 times higher than the accuracy of the forecast model based on the currently used network indicators.

• Asia pacific journal of information systems
• /
• v.22 no.4
• /
• pp.101-123
• /
• 2012

Currently, Social Media, it has widely a renown keyword and its related social trends and businesses have been fastly applied into various contexts. Social media has become an important research area for scholars interested in online technologies and cyber space and their social impacts. Social media is not only including web-based services but also mobile-based application services that allow people to share various style information and knowledge through online connection. Social media users have tendency to common identity- and bond-attachment through interactions such as 'thumbs up', 'reply note', 'forwarding', which may have driven from various factors and may result in delivering information, sharing knowledge, and specific experiences et al. Even further, almost of all social media sites provide and connect unknown strangers depending on shared interests, political views, or enjoyable activities, and other stuffs incorporating the creation of contents, which provides benefits to users. As fast developing digital devices including smartphone, tablet PC, internet based blogging, and photo and video clips, scholars desperately have began to study regarding diverse issues connecting human beings' motivations and the behavioral results which may be articulated by the format of antecedents as well as consequences related to contents that people create via social media. Social media such as Facebook, Twitter, or Cyworld users are more and more getting close each other and build up their relationships by a different style. In this sense, people use social media as tools for maintain pre-existing network, creating new people socially, and at the same time, explicitly find some business opportunities using personal and unlimited public networks. In terms of theory in explaining this phenomenon, social capital is a concept that describes the benefits one receives from one's relationship with others. Thereby, social media use is closely related to the form and connected of people, which is a bridge that can be able to achieve informational benefits of a heterogeneous network of people and common identity- and bonding-attachment which emphasizes emotional benefits from community members or friend group. Social capital would be resources accumulated through the relationships among people, which can be considered as an investment in social relations with expected returns and may achieve benefits from the greater access to and use of resources embedded in social networks. Social media using for their social capital has vastly been adopted in a cyber world, however, there has been little explaining the phenomenon theoretically how people may take advantages or opportunities through interaction among people, why people may interactively give willingness to help or their answers. The individual consciously express themselves in an online space, so called, common identity- or bonding-attachments. Common-identity attachment is the focus of the weak ties, which are loose connections between individuals who may provide useful information or new perspectives for one another but typically not emotional support, whereas common-bonding attachment is explained that between individuals in tightly-knit, emotionally close relationship such as family and close friends. The common identify- and bonding-attachment are mainly studying on-offline setting, which individual convey an impression to others that are expressed to own interest to others. Thus, individuals expect to meet other people and are trying to behave self-presentation engaging in opposite partners accordingly. As developing social media, individuals are motivated to disclose self-disclosures of open and honest using diverse cues such as verbal and nonverbal and pictorial and video files to their friends as well as passing strangers. Social media context, common identity- and bond-attachment for self-presentation seems different compared with face-to-face context. In the realm of social media, social users look for self-impression by posting text messages, pictures, video files. Under the digital environments, people interact to work, shop, learn, entertain, and be played. Social media provides increasingly the kinds of intention and behavior in online. Typically, identity and bond social capital through self-presentation is the intentional and tangible component of identity. At social media, people try to engage in others via a desired impression, which can maintain through performing coherent and complementary communications including displaying signs, symbols, brands made of digital stuffs(information, interest, pictures, etc,). In marketing area, consumers traditionally show common-identity as they select clothes, hairstyles, automobiles, logos, and so on, to impress others in any given context in a shopping mall or opera. To examine these social capital and attachment, we combined a social capital theory with an attachment theory into our research model. Our research model focuses on the common identity- and bond-attachment how they are formulated through social capitals: cognitive capital, structural capital, relational capital, and individual characteristics. Thus, we examined that individual online kindness, self-rated expertise, and social relation influence to build common identity- and bond-attachment, and the attachment effects make an impact on both the willingness to help, however, common bond seems not to show directly impact on information sharing. As a result, we discover that the social capital and attachment theories are mainly applicable to the context of social media and usage in the individual networks. We collected sample data of 256 who are using social media such as Facebook, Twitter, and Cyworld and analyzed the suggested hypotheses through the Structural Equation Model by AMOS. This study analyzes the direct and indirect relationship between the social network service usage and outcomes. Antecedents of kindness, confidence of knowledge, social relations are significantly affected to the mediators common identity-and bond attachments, however, interestingly, network externality does not impact, which we assumed that a size of network was a negative because group members would not significantly contribute if the members do not intend to actively interact with each other. The mediating variables had a positive effect on toward willingness to help. Further, common identity attachment has stronger significant on shared information.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.163-176
• /
• 2014

Social media is becoming the platform for users to communicate their activities, status, emotions, and experiences to other people. In recent years, microblogs, such as Twitter, have gained in popularity because of its ease of use, speed, and reach. Compared to a conventional web blog, a microblog lowers users' efforts and investment for content generation by recommending shorter posts. There has been a lot research into capturing the social phenomena and analyzing the chatter of microblogs. However, measuring television ratings has been given little attention so far. Currently, the most common method to measure TV ratings uses an electronic metering device installed in a small number of sampled households. Microblogs allow users to post short messages, share daily updates, and conveniently keep in touch. In a similar way, microblog users are interacting with each other while watching television or movies, or visiting a new place. In order to measure TV ratings, some features are significant during certain hours of the day, or days of the week, whereas these same features are meaningless during other time periods. Thus, the importance of features can change during the day, and a model capturing the time sensitive relevance is required to estimate TV ratings. Therefore, modeling time-related characteristics of features should be a key when measuring the TV ratings through microblogs. We show that capturing time-dependency of features in measuring TV ratings is vitally necessary for improving their accuracy. To explore the relationship between the content of microblogs and TV ratings, we collected Twitter data using the Get Search component of the Twitter REST API from January 2013 to October 2013. There are about 300 thousand posts in our data set for the experiment. After excluding data such as adverting or promoted tweets, we selected 149 thousand tweets for analysis. The number of tweets reaches its maximum level on the broadcasting day and increases rapidly around the broadcasting time. This result is stems from the characteristics of the public channel, which broadcasts the program at the predetermined time. From our analysis, we find that count-based features such as the number of tweets or retweets have a low correlation with TV ratings. This result implies that a simple tweet rate does not reflect the satisfaction or response to the TV programs. Content-based features extracted from the content of tweets have a relatively high correlation with TV ratings. Further, some emoticons or newly coined words that are not tagged in the morpheme extraction process have a strong relationship with TV ratings. We find that there is a time-dependency in the correlation of features between the before and after broadcasting time. Since the TV program is broadcast at the predetermined time regularly, users post tweets expressing their expectation for the program or disappointment over not being able to watch the program. The highly correlated features before the broadcast are different from the features after broadcasting. This result explains that the relevance of words with TV programs can change according to the time of the tweets. Among the 336 words that fulfill the minimum requirements for candidate features, 145 words have the highest correlation before the broadcasting time, whereas 68 words reach the highest correlation after broadcasting. Interestingly, some words that express the impossibility of watching the program show a high relevance, despite containing a negative meaning. Understanding the time-dependency of features can be helpful in improving the accuracy of TV ratings measurement. This research contributes a basis to estimate the response to or satisfaction with the broadcasted programs using the time dependency of words in Twitter chatter. More research is needed to refine the methodology for predicting or measuring TV ratings.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.49-65
• /
• 2014

Word of Mouth (WOM) is a behavior used by consumers to transfer or communicate their product or service experience to other consumers. Due to the popularity of social media such as Facebook, Twitter, blogs, and online communities, electronic WOM (e-WOM) has become important to the success of products or services. As a result, most enterprises pay close attention to e-WOM for their products or services. This is especially important for movies, as these are experiential products. This paper aims to identify the network factors of an online movie community that impact box office revenue using social network analysis. In addition to traditional WOM factors (volume and valence of WOM), network centrality measures of the online community are included as influential factors in box office revenue. Based on previous research results, we develop five hypotheses on the relationships between potential influential factors (WOM volume, WOM valence, degree centrality, betweenness centrality, closeness centrality) and box office revenue. The first hypothesis is that the accumulated volume of WOM in online product communities is positively related to the total revenue of movies. The second hypothesis is that the accumulated valence of WOM in online product communities is positively related to the total revenue of movies. The third hypothesis is that the average of degree centralities of reviewers in online product communities is positively related to the total revenue of movies. The fourth hypothesis is that the average of betweenness centralities of reviewers in online product communities is positively related to the total revenue of movies. The fifth hypothesis is that the average of betweenness centralities of reviewers in online product communities is positively related to the total revenue of movies. To verify our research model, we collect movie review data from the Internet Movie Database (IMDb), which is a representative online movie community, and movie revenue data from the Box-Office-Mojo website. The movies in this analysis include weekly top-10 movies from September 1, 2012, to September 1, 2013, with in total. We collect movie metadata such as screening periods and user ratings; and community data in IMDb including reviewer identification, review content, review times, responder identification, reply content, reply times, and reply relationships. For the same period, the revenue data from Box-Office-Mojo is collected on a weekly basis. Movie community networks are constructed based on reply relationships between reviewers. Using a social network analysis tool, NodeXL, we calculate the averages of three centralities including degree, betweenness, and closeness centrality for each movie. Correlation analysis of focal variables and the dependent variable (final revenue) shows that three centrality measures are highly correlated, prompting us to perform multiple regressions separately with each centrality measure. Consistent with previous research results, our regression analysis results show that the volume and valence of WOM are positively related to the final box office revenue of movies. Moreover, the averages of betweenness centralities from initial community networks impact the final movie revenues. However, both of the averages of degree centralities and closeness centralities do not influence final movie performance. Based on the regression results, three hypotheses, 1, 2, and 4, are accepted, and two hypotheses, 3 and 5, are rejected. This study tries to link the network structure of e-WOM on online product communities with the product's performance. Based on the analysis of a real online movie community, the results show that online community network structures can work as a predictor of movie performance. The results show that the betweenness centralities of the reviewer community are critical for the prediction of movie performance. However, degree centralities and closeness centralities do not influence movie performance. As future research topics, similar analyses are required for other product categories such as electronic goods and online content to generalize the study results.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.95-110
• /
• 2013

Recently, the amount of unstructured data being generated through a variety of social media has been increasing rapidly, resulting in the increasing need to collect, store, search for, analyze, and visualize this data. This kind of data cannot be handled appropriately by using the traditional methodologies usually used for analyzing structured data because of its vast volume and unstructured nature. In this situation, many attempts are being made to analyze unstructured data such as text files and log files through various commercial or noncommercial analytical tools. Among the various contemporary issues dealt with in the literature of unstructured text data analysis, the concepts and techniques of opinion mining have been attracting much attention from pioneer researchers and business practitioners. Opinion mining or sentiment analysis refers to a series of processes that analyze participants' opinions, sentiments, evaluations, attitudes, and emotions about selected products, services, organizations, social issues, and so on. In other words, many attempts based on various opinion mining techniques are being made to resolve complicated issues that could not have otherwise been solved by existing traditional approaches. One of the most representative attempts using the opinion mining technique may be the recent research that proposed an intelligent model for predicting the direction of the stock index. This model works mainly on the basis of opinions extracted from an overwhelming number of economic news repots. News content published on various media is obviously a traditional example of unstructured text data. Every day, a large volume of new content is created, digitalized, and subsequently distributed to us via online or offline channels. Many studies have revealed that we make better decisions on political, economic, and social issues by analyzing news and other related information. In this sense, we expect to predict the fluctuation of stock markets partly by analyzing the relationship between economic news reports and the pattern of stock prices. So far, in the literature on opinion mining, most studies including ours have utilized a sentiment dictionary to elicit sentiment polarity or sentiment value from a large number of documents. A sentiment dictionary consists of pairs of selected words and their sentiment values. Sentiment classifiers refer to the dictionary to formulate the sentiment polarity of words, sentences in a document, and the whole document. However, most traditional approaches have common limitations in that they do not consider the flexibility of sentiment polarity, that is, the sentiment polarity or sentiment value of a word is fixed and cannot be changed in a traditional sentiment dictionary. In the real world, however, the sentiment polarity of a word can vary depending on the time, situation, and purpose of the analysis. It can also be contradictory in nature. The flexibility of sentiment polarity motivated us to conduct this study. In this paper, we have stated that sentiment polarity should be assigned, not merely on the basis of the inherent meaning of a word but on the basis of its ad hoc meaning within a particular context. To implement our idea, we presented an intelligent investment decision-support model based on opinion mining that performs the scrapping and parsing of massive volumes of economic news on the web, tags sentiment words, classifies sentiment polarity of the news, and finally predicts the direction of the next day's stock index. In addition, we applied a domain-specific sentiment dictionary instead of a general purpose one to classify each piece of news as either positive or negative. For the purpose of performance evaluation, we performed intensive experiments and investigated the prediction accuracy of our model. For the experiments to predict the direction of the stock index, we gathered and analyzed 1,072 articles about stock markets published by "M" and "E" media between July 2011 and September 2011.