• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.19-41
• /
• 2019

According to the rapidly increasing demand for text data analysis, research and investment in text mining are being actively conducted not only in academia but also in various industries. Text mining is generally conducted in two steps. In the first step, the text of the collected document is tokenized and structured to convert the original document into a computer-readable form. In the second step, tasks such as document classification, clustering, and topic modeling are conducted according to the purpose of analysis. Until recently, text mining-related studies have been focused on the application of the second steps, such as document classification, clustering, and topic modeling. However, with the discovery that the text structuring process substantially influences the quality of the analysis results, various embedding methods have actively been studied to improve the quality of analysis results by preserving the meaning of words and documents in the process of representing text data as vectors. Unlike structured data, which can be directly applied to a variety of operations and traditional analysis techniques, Unstructured text should be preceded by a structuring task that transforms the original document into a form that the computer can understand before analysis. It is called "Embedding" that arbitrary objects are mapped to a specific dimension space while maintaining algebraic properties for structuring the text data. Recently, attempts have been made to embed not only words but also sentences, paragraphs, and entire documents in various aspects. Particularly, with the demand for analysis of document embedding increases rapidly, many algorithms have been developed to support it. Among them, doc2Vec which extends word2Vec and embeds each document into one vector is most widely used. However, the traditional document embedding method represented by doc2Vec generates a vector for each document using the whole corpus included in the document. This causes a limit that the document vector is affected by not only core words but also miscellaneous words. Additionally, the traditional document embedding schemes usually map each document into a single corresponding vector. Therefore, it is difficult to represent a complex document with multiple subjects into a single vector accurately using the traditional approach. In this paper, we propose a new multi-vector document embedding method to overcome these limitations of the traditional document embedding methods. This study targets documents that explicitly separate body content and keywords. In the case of a document without keywords, this method can be applied after extract keywords through various analysis methods. However, since this is not the core subject of the proposed method, we introduce the process of applying the proposed method to documents that predefine keywords in the text. The proposed method consists of (1) Parsing, (2) Word Embedding, (3) Keyword Vector Extraction, (4) Keyword Clustering, and (5) Multiple-Vector Generation. The specific process is as follows. all text in a document is tokenized and each token is represented as a vector having N-dimensional real value through word embedding. After that, to overcome the limitations of the traditional document embedding method that is affected by not only the core word but also the miscellaneous words, vectors corresponding to the keywords of each document are extracted and make up sets of keyword vector for each document. Next, clustering is conducted on a set of keywords for each document to identify multiple subjects included in the document. Finally, a Multi-vector is generated from vectors of keywords constituting each cluster. The experiments for 3.147 academic papers revealed that the single vector-based traditional approach cannot properly map complex documents because of interference among subjects in each vector. With the proposed multi-vector based method, we ascertained that complex documents can be vectorized more accurately by eliminating the interference among subjects.

• Korean Journal of Environmental Biology
• /
• v.40 no.4
• /
• pp.413-422
• /
• 2022

Barnea manilensis is a bivalve which bores soft rocks, such as, limestone or mudstone in the low intertidal zone. They make burrows which have narrow entrances and wide interiors and live in these burrows for a lifetime. In this study, the morphology and the microstructure of the valve of rock-boring clam B. manilensis were observed using a stereoscopic microscope and FE-SEM, respectively. The chemical composition of specific part of the valve was assessed by energy dispersive X-ray spectroscopy (EDS) analysis. 3D modeling and structural dynamic analysis were used to simulate the boring behavior of B. manilensis. Microscopy results showed that the valve was asymmetric with plow-like spikes which were located on the anterior surface of the valve and were distributed in a specific direction. The anterior parts of the valve were thicker than the posterior parts. EDS results indicated that the valve mainly consisted of calcium carbonate, while metal elements, such as, Al, Si, Mn, Fe, and Mg were detected on the outer surface of the anterior spikes. It was assumed that the metal elements increased the strength of the valve, thus helping the B. manilensis to bore sediment. The simulation showed that spikes located on the anterior part of the valve received a load at all angles. It was suggested that the anterior part of the shell received the load while drilling rocks. The boring mechanism using the amorphous valve of B. manilensis is expected to be used as basic data to devise an efficient drilling mechanism.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.20 no.2
• /
• pp.57-72
• /
• 2018

In order to extract meaningful information from the excellent farming settlement cases of young farmers published by KNCAF, we studied the key words with text mining and created a word cloud for visualization. First, in the text mining results for the entire sample, the words 'CEO', 'corporate executive', 'think', 'self', 'start', 'mind', and 'effort' are the words with high frequency among the top 50 core words. Their ability to think, judge and push ahead with themselves is a result of showing that they have ability of to be managers or managers. And it is a expression of how they manages to achieve their dream without giving up their dream. The high frequency of words such as "father" and "parent" is due to the high ratio of parents' cooperation and succession. Also 'KNCAF', 'university', 'graduation' and 'study' are the results of their high educational awareness, and 'organic farming' and 'eco-friendly' are the result of the interest in eco-friendly agriculture. In addition, words related to the 6th industry such as 'sales' and 'experience' represent their efforts to revitalize farming and fishing villages. Meanwhile, 'internet', 'blog', 'online', 'SNS', 'ICT', 'composite' and 'smart' were not included in the top 50. However, the fact that these words were extracted without omission shows that young farmers are increasingly interested in the scientificization and high-tech of agriculture and fisheries Next, as a result of grouping the top 50 key words by crop, the words 'facilities' in livestock, vegetables and aquatic crops, the words 'equipment' and 'machine' in food crops were extracted as main words. 'Eco-friendly' and 'organic' appeared in vegetable crops and food crops, and 'organic' appeared in fruit crops. The 'worm' of eco-friendly farming method appeared in the food crops, and the 'certification', which means excellent agricultural and marine products, appeared only in the fishery crops. 'Production', which is related to '6th industry', appeared in all crops, 'processing' and 'distribution' appeared in the fruit crops, and 'experience' appeared in the vegetable crops, food crops and fruit crops. To visualize the extracted words by text mining, we created a word cloud with the entire samples and each crop sample. As a result, we were able to judge the meaning of excellent practices, which are unstructured text, by character size.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.