A Study on Knowledge Entity Extraction Method for Individual Stocks Based on Neural Tensor Network (뉴럴 텐서 네트워크 기반 주식 개별종목 지식개체명 추출 방법에 관한 연구)
-
- Journal of Intelligence and Information Systems
- /
- v.25 no.2
- /
- pp.25-38
- /
- 2019
Selecting high-quality information that meets the interests and needs of users among the overflowing contents is becoming more important as the generation continues. In the flood of information, efforts to reflect the intention of the user in the search result better are being tried, rather than recognizing the information request as a simple string. Also, large IT companies such as Google and Microsoft focus on developing knowledge-based technologies including search engines which provide users with satisfaction and convenience. Especially, the finance is one of the fields expected to have the usefulness and potential of text data analysis because it's constantly generating new information, and the earlier the information is, the more valuable it is. Automatic knowledge extraction can be effective in areas where information flow is vast, such as financial sector, and new information continues to emerge. However, there are several practical difficulties faced by automatic knowledge extraction. First, there are difficulties in making corpus from different fields with same algorithm, and it is difficult to extract good quality triple. Second, it becomes more difficult to produce labeled text data by people if the extent and scope of knowledge increases and patterns are constantly updated. Third, performance evaluation is difficult due to the characteristics of unsupervised learning. Finally, problem definition for automatic knowledge extraction is not easy because of ambiguous conceptual characteristics of knowledge. So, in order to overcome limits described above and improve the semantic performance of stock-related information searching, this study attempts to extract the knowledge entity by using neural tensor network and evaluate the performance of them. Different from other references, the purpose of this study is to extract knowledge entity which is related to individual stock items. Various but relatively simple data processing methods are applied in the presented model to solve the problems of previous researches and to enhance the effectiveness of the model. From these processes, this study has the following three significances. First, A practical and simple automatic knowledge extraction method that can be applied. Second, the possibility of performance evaluation is presented through simple problem definition. Finally, the expressiveness of the knowledge increased by generating input data on a sentence basis without complex morphological analysis. The results of the empirical analysis and objective performance evaluation method are also presented. The empirical study to confirm the usefulness of the presented model, experts' reports about individual 30 stocks which are top 30 items based on frequency of publication from May 30, 2017 to May 21, 2018 are used. the total number of reports are 5,600, and 3,074 reports, which accounts about 55% of the total, is designated as a training set, and other 45% of reports are designated as a testing set. Before constructing the model, all reports of a training set are classified by stocks, and their entities are extracted using named entity recognition tool which is the KKMA. for each stocks, top 100 entities based on appearance frequency are selected, and become vectorized using one-hot encoding. After that, by using neural tensor network, the same number of score functions as stocks are trained. Thus, if a new entity from a testing set appears, we can try to calculate the score by putting it into every single score function, and the stock of the function with the highest score is predicted as the related item with the entity. To evaluate presented models, we confirm prediction power and determining whether the score functions are well constructed by calculating hit ratio for all reports of testing set. As a result of the empirical study, the presented model shows 69.3% hit accuracy for testing set which consists of 2,526 reports. this hit ratio is meaningfully high despite of some constraints for conducting research. Looking at the prediction performance of the model for each stocks, only 3 stocks, which are LG ELECTRONICS, KiaMtr, and Mando, show extremely low performance than average. this result maybe due to the interference effect with other similar items and generation of new knowledge. In this paper, we propose a methodology to find out key entities or their combinations which are necessary to search related information in accordance with the user's investment intention. Graph data is generated by using only the named entity recognition tool and applied to the neural tensor network without learning corpus or word vectors for the field. From the empirical test, we confirm the effectiveness of the presented model as described above. However, there also exist some limits and things to complement. Representatively, the phenomenon that the model performance is especially bad for only some stocks shows the need for further researches. Finally, through the empirical study, we confirmed that the learning method presented in this study can be used for the purpose of matching the new text information semantically with the related stocks.
The Korean film industry with significant increase every year exceeded the number of cumulative audiences of 200 million people in 2013 finally. However, starting from 2015 the Korean film industry entered a period of low growth and experienced a negative growth after all in 2016. To overcome such difficulty, stakeholders like production company, distribution company, multiplex have attempted to maximize the market returns using strategies of predicting change of market and of responding to such market change immediately. Since a film is classified as one of experiential products, it is not easy to predict a box office record and the initial number of audiences before the film is released. And also, the number of audiences fluctuates with a variety of factors after the film is released. So, the production company and distribution company try to be guaranteed the number of screens at the opining time of a newly released by multiplex chains. However, the multiplex chains tend to open the screening schedule during only a week and then determine the number of screening of the forthcoming week based on the box office record and the evaluation of audiences. Many previous researches have conducted to deal with the prediction of box office records of films. In the early stage, the researches attempted to identify factors affecting the box office record. And nowadays, many studies have tried to apply various analytic techniques to the factors identified previously in order to improve the accuracy of prediction and to explain the effect of each factor instead of identifying new factors affecting the box office record. However, most of previous researches have limitations in that they used the total number of audiences from the opening to the end as a target variable, and this makes it difficult to predict and respond to the demand of market which changes dynamically. Therefore, the purpose of this study is to predict the weekly number of audiences of a newly released film so that the stakeholder can flexibly and elastically respond to the change of the number of audiences in the film. To that end, we considered the factors used in the previous studies affecting box office and developed new factors not used in previous studies such as the order of opening of movies, dynamics of sales. Along with the comprehensive factors, we used the machine learning method such as Random Forest, Multi Layer Perception, Support Vector Machine, and Naive Bays, to predict the number of cumulative visitors from the first week after a film release to the third week. At the point of the first and the second week, we predicted the cumulative number of visitors of the forthcoming week for a released film. And at the point of the third week, we predict the total number of visitors of the film. In addition, we predicted the total number of cumulative visitors also at the point of the both first week and second week using the same factors. As a result, we found the accuracy of predicting the number of visitors at the forthcoming week was higher than that of predicting the total number of them in all of three weeks, and also the accuracy of the Random Forest was the highest among the machine learning methods we used. This study has implications in that this study 1) considered various factors comprehensively which affect the box office record and merely addressed by other previous researches such as the weekly rating of audiences after release, the weekly rank of the film after release, and the weekly sales share after release, and 2) tried to predict and respond to the demand of market which changes dynamically by suggesting models which predicts the weekly number of audiences of newly released films so that the stakeholders can flexibly and elastically respond to the change of the number of audiences in the film.
In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.
With the development of media, the methods for the documentation of intangible cultural heritage have been also developed and diversified. As well as the previous analogue ways of documentation, the have been recently applying new multi-media technologies focusing on digital pictures, sound sources, movies, etc. Among the new technologies, the documentation of intangible cultural heritage using the method of 'Motion Capture' has proved itself prominent especially in the fields that require three-dimensional documentation such as dances and performances. Motion Capture refers to the documentation technology which records the signals of the time varing positions derived from the sensors equipped on the surface of an object. It converts the signals from the sensors into digital data which can be plotted as points on the virtual coordinates of the computer and records the movement of the points during a certain period of time, as the object moves. It produces scientific data for the preservation of intangible cultural heritage, by displaying digital data which represents the virtual motion of a holder of an intangible cultural heritage. National Research Institute of Cultural Properties (NRICP) has been working on for the development of new documentation method for the Important Intangible Cultural Heritage designated by Korean government. This is to be done using 'motion capture' equipments which are also widely used for the computer graphics in movie or game industries. This project is designed to apply the motion capture technology for 3 years- from 2005 to 2007 - for 11 performances from 7 traditional dances of which body gestures have considerable values among the Important Intangible Cultural Heritage performances. This is to be supported by lottery funds. In 2005, the first year of the project, accumulated were data of single dances, such as Seungmu (monk's dance), Salpuri(a solo dance for spiritual cleansing dance), Taepyeongmu (dance of peace), which are relatively easy in terms of performing skills. In 2006, group dances, such as Jinju Geommu (Jinju sword dance), Seungjeonmu (dance for victory), Cheoyongmu (dance of Lord Cheoyong), etc., will be documented. In the last year of the project, 2007, education programme for comparative studies, analysis and transmission of intangible cultural heritage and three-dimensional contents for public service will be devised, based on the accumulated data, as well as the documentation of Hakyeonhwadae Habseolmu (crane dance combined with the lotus blossom dance). By describing the processes and results of motion capture documentation of Salpuri dance (Lee Mae-bang), Taepyeongmu (Kang seon-young) and Seungmu (Lee Mae-bang, Lee Ae-ju and Jung Jae-man) conducted in 2005, this report introduces a new approach for the documentation of intangible cultural heritage. During the first year of the project, two questions have been raised. First, how can we capture motions of a holder (dancer) without cutoffs during quite a long performance? After many times of tests, the motion capture system proved itself stable with continuous results. Second, how can we reproduce the accurate motion without the re-targeting process? The project re-created the most accurate motion of the dancer's gestures, applying the new technology to drew out the shape of the dancers's body digital data before the motion capture process for the first time in Korea. The accurate three-dimensional body models for four holders obtained by the body scanning enhanced the accuracy of the motion capture of the dance.
As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.
For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.
This study uses Node2vec graph embedding method and Light GBM link prediction to explore undeveloped export candidate countries in Korea's food and beverage industry. Node2vec is the method that improves the limit of the structural equivalence representation of the network, which is known to be relatively weak compared to the existing link prediction method based on the number of common neighbors of the network. Therefore, the method is known to show excellent performance in both community detection and structural equivalence of the network. The vector value obtained by embedding the network in this way operates under the condition of a constant length from an arbitrarily designated starting point node. Therefore, it has the advantage that it is easy to apply the sequence of nodes as an input value to the model for downstream tasks such as Logistic Regression, Support Vector Machine, and Random Forest. Based on these features of the Node2vec graph embedding method, this study applied the above method to the international trade information of the Korean food and beverage industry. Through this, we intend to contribute to creating the effect of extensive margin diversification in Korea in the global value chain relationship of the industry. The optimal predictive model derived from the results of this study recorded a precision of 0.95 and a recall of 0.79, and an F1 score of 0.86, showing excellent performance. This performance was shown to be superior to that of the binary classifier based on Logistic Regression set as the baseline model. In the baseline model, a precision of 0.95 and a recall of 0.73 were recorded, and an F1 score of 0.83 was recorded. In addition, the light GBM-based optimal prediction model derived from this study showed superior performance than the link prediction model of previous studies, which is set as a benchmarking model in this study. The predictive model of the previous study recorded only a recall rate of 0.75, but the proposed model of this study showed better performance which recall rate is 0.79. The difference in the performance of the prediction results between benchmarking model and this study model is due to the model learning strategy. In this study, groups were classified by the trade value scale, and prediction models were trained differently for these groups. Specific methods are (1) a method of randomly masking and learning a model for all trades without setting specific conditions for trade value, (2) arbitrarily masking a part of the trades with an average trade value or higher and using the model method, and (3) a method of arbitrarily masking some of the trades with the top 25% or higher trade value and learning the model. As a result of the experiment, it was confirmed that the performance of the model trained by randomly masking some of the trades with the above-average trade value in this method was the best and appeared stably. It was found that most of the results of potential export candidates for Korea derived through the above model appeared appropriate through additional investigation. Combining the above, this study could suggest the practical utility of the link prediction method applying Node2vec and Light GBM. In addition, useful implications could be derived for weight update strategies that can perform better link prediction while training the model. On the other hand, this study also has policy utility because it is applied to trade transactions that have not been performed much in the research related to link prediction based on graph embedding. The results of this study support a rapid response to changes in the global value chain such as the recent US-China trade conflict or Japan's export regulations, and I think that it has sufficient usefulness as a tool for policy decision-making.
From January 2020 to October 2021, more than 500,000 academic studies related to COVID-19 (Coronavirus-2, a fatal respiratory syndrome) have been published. The rapid increase in the number of papers related to COVID-19 is putting time and technical constraints on healthcare professionals and policy makers to quickly find important research. Therefore, in this study, we propose a method of extracting useful information from text data of extensive literature using LDA and Word2vec algorithm. Papers related to keywords to be searched were extracted from papers related to COVID-19, and detailed topics were identified. The data used the CORD-19 data set on Kaggle, a free academic resource prepared by major research groups and the White House to respond to the COVID-19 pandemic, updated weekly. The research methods are divided into two main categories. First, 41,062 articles were collected through data filtering and pre-processing of the abstracts of 47,110 academic papers including full text. For this purpose, the number of publications related to COVID-19 by year was analyzed through exploratory data analysis using a Python program, and the top 10 journals under active research were identified. LDA and Word2vec algorithm were used to derive research topics related to COVID-19, and after analyzing related words, similarity was measured. Second, papers containing 'vaccine' and 'treatment' were extracted from among the topics derived from all papers, and a total of 4,555 papers related to 'vaccine' and 5,971 papers related to 'treatment' were extracted. did For each collected paper, detailed topics were analyzed using LDA and Word2vec algorithms, and a clustering method through PCA dimension reduction was applied to visualize groups of papers with similar themes using the t-SNE algorithm. A noteworthy point from the results of this study is that the topics that were not derived from the topics derived for all papers being researched in relation to COVID-19 (