• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.744-751
• /
• 2022

Construction is among the most dangerous industries with numerous accidents occurring at job sites. Following an accident, an investigation report is issued, containing all of the specifics. Analyzing the text information in construction accident reports can help enhance our understanding of historical data and be utilized for accident prevention. However, the conventional method requires a significant amount of time and effort to read and identify crucial information. The previous studies primarily focused on analyzing related objects and causes of accidents rather than the construction activities. This study aims to extract construction activities taken by workers associated with accidents by presenting an automated framework that adopts a deep learning-based approach and natural language processing (NLP) techniques to automatically classify sentences obtained from previous construction accident reports into predefined categories, namely TRADE (i.e., a construction activity before an accident), EVENT (i.e., an accident), and CONSEQUENCE (i.e., the outcome of an accident). The classification model was developed using Convolutional Neural Network (CNN) showed a robust accuracy of 88.7%, indicating that the proposed model is capable of investigating the occurrence of accidents with minimal manual involvement and sophisticated engineering. Also, this study is expected to support safety assessments and build risk management systems.

• Journal of KIISE
• /
• v.43 no.9
• /
• pp.983-997
• /
• 2016

Many available online product reviews for any given product makes it difficult for a consumer to locate the helpful reviews. The purpose of this study was to investigate automatic helpfulness evaluation of online product reviews according to review information types based on the target of information. The underlying assumption was that consumers find reviews containing specific information related to the product itself or the reliability of reviewers more helpful than peripheral information, such as shipping or customer service. Therefore, each sentence was categorized by given information types, which reduced the semantic space of review sentences. Subsequently, we extracted specific information from sentences by using a topic-based representation of the sentences and a clustering algorithm. Review ranking experiments indicated more effective results than other comparable approaches.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.309-311
• /
• 2014

Despite increasing demands for big data application based on the analysis of scattered unstructured data, few relevant studies have been reported. Accordingly, the present study suggests a technique enabling a sentence-based semantic analysis by extracting objects from collected web information and automatically analyzing the relationships between such objects with collective intelligence and language processing technology. To be specific, collected information is stored in DBMS in a structured form, and then morpheme and feature information is analyzed. Obtained morphemes are classified into objects of interest, marginal objects and objects of non-interest. Then, with an inter-object attribute recognition technique, the relationships between objects are analyzed in terms of the degree, scope and nature of such relationships. As a result, the analysis of relevance between the information was based on certain keywords and used an inter-object relationship extraction technique that can determine positivity and negativity. Also, the present study suggested a method to design a system fit for real-time large-capacity processing and applicable to high value-added services.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.1
• /
• pp.149-157
• /
• 2010

As the use of the Internet has recently increased, the demand for opinion information posted on the Internet has grown. However, such resources only exist on the website. People who want to search for information on the Internet find it inconvenient to visit each website. This paper focuses on the opinion information extraction and analysis system through Web mining that is based on statistics collected from Web contents. That is, users' opinion information which is scattered across several websites can be automatically analyzed and extracted. The system provides the opinion information search service that enables users to search for real-time positive and negative opinions and check their statistics. Also, users can do real-time search and monitoring about other opinion information by putting keywords in the system. Proposed technologies proved to have outstanding capabilities in comparison to existing ones through tests. The capabilities to extract positive and negative opinion information were assessed. Specifically, test movie review sentence testing data was tested and its results were analyzed.

• Korean Journal of Cognitive Science
• /
• v.12 no.1_2
• /
• pp.35-42
• /
• 2001

In this paper. a document is represented as a weighted graph called a text relationship map. In the graph. a node represents a vector of nouns in a sentence, an edge completely connects other nodes. and a weight on the edge is a value of the similarity between two nodes. The similarity is based on the word overlap between the corresponding nodes. The importance of a node. called an aggregate similarity in this paper. is defined as the sum of weights on the links connecting it to other nodes on the map. In this paper. we present a Korean text summarization system using the aggregate similarity. To evaluate our system, we used two test collection, one collection (PAPER-InCon) consists of 100 papers in the field of computer science: the other collection (NEWS) is composed of 105 articles in the newspapers and had built by KOROlC. Under the compression rate of 20%. we achieved the recall of 46.6% (PAPER-InCon) and 30.5% (NEWS) and the precision of 76.9% (PAPER-InCon) and 42.3% (NEWS).

• 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.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.120-126
• /
• 2009

As the information age grows rapidly, the amount of digital texts has been increasing as well. It has brought an increasing of visualization case in order to figure out lots of digital texts. Existing visualized design of digital text is merely concentrating on figuration of subject word through adoption of stemming algorithm and word frequency extraction, prominence of meaning of text, and connection in between sentences. So it is a fact that expression of rhythm that can visualize sentimental feeing of digital text was insufficient. Syllable is a phoneme unit that can express rhythm more efficiently. In sentences, syllable is a most basic pronunciation unit in pronouncing word, phase and sentence. On this basis, accent, intonation, length of rhythm factor and others are based on syllable. Sonority, which is most closely associated with definitions of syllable, is expressed through air flow of igniting lung and acoustic energy that is specified kinetic energy into sonority. Seen from this perspective, this study examines phonologic definition and characteristics based on syllable, which is properties of digital text, and research the way to visualize rhythm through diagram. After converting digital text into phonetic symbol by the experiment, rhythm information are visualized into images using degree of resonance, which was started from rhythm in all languages, and using syllable establishment of digital text. By visualizing syllable information, it provides syllable information of digital text and express sentiment of digital text through diagram to assist user's understanding by systematic formula. Therefore, this study is aimed at planning for easy understanding of text's rhythm and realizing visualization of digital text.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.131-150
• /
• 2015

Omission of noun phrases for obligatory cases is a common phenomenon in sentences of Korean and Japanese, which is not observed in English. When an argument of a predicate can be filled with a noun phrase co-referential with the title, the argument is more easily omitted in Encyclopedia texts. The omitted noun phrase is called a zero anaphor or zero pronoun. Encyclopedias like Wikipedia are major source for information extraction by intelligent application systems such as information retrieval and question answering systems. However, omission of noun phrases makes the quality of information extraction poor. This paper deals with the problem of developing a system that can restore omitted noun phrases in encyclopedia documents. The problem that our system deals with is almost similar to zero anaphora resolution which is one of the important problems in natural language processing. A noun phrase existing in the text that can be used for restoration is called an antecedent. An antecedent must be co-referential with the zero anaphor. While the candidates for the antecedent are only noun phrases in the same text in case of zero anaphora resolution, the title is also a candidate in our problem. In our system, the first stage is in charge of detecting the zero anaphor. In the second stage, antecedent search is carried out by considering the candidates. If antecedent search fails, an attempt made, in the third stage, to use the title as the antecedent. The main characteristic of our system is to make use of a structural SVM for finding the antecedent. The noun phrases in the text that appear before the position of zero anaphor comprise the search space. The main technique used in the methods proposed in previous research works is to perform binary classification for all the noun phrases in the search space. The noun phrase classified to be an antecedent with highest confidence is selected as the antecedent. However, we propose in this paper that antecedent search is viewed as the problem of assigning the antecedent indicator labels to a sequence of noun phrases. In other words, sequence labeling is employed in antecedent search in the text. We are the first to suggest this idea. To perform sequence labeling, we suggest to use a structural SVM which receives a sequence of noun phrases as input and returns the sequence of labels as output. An output label takes one of two values: one indicating that the corresponding noun phrase is the antecedent and the other indicating that it is not. The structural SVM we used is based on the modified Pegasos algorithm which exploits a subgradient descent methodology used for optimization problems. To train and test our system we selected a set of Wikipedia texts and constructed the annotated corpus in which gold-standard answers are provided such as zero anaphors and their possible antecedents. Training examples are prepared using the annotated corpus and used to train the SVMs and test the system. For zero anaphor detection, sentences are parsed by a syntactic analyzer and subject or object cases omitted are identified. Thus performance of our system is dependent on that of the syntactic analyzer, which is a limitation of our system. When an antecedent is not found in the text, our system tries to use the title to restore the zero anaphor. This is based on binary classification using the regular SVM. The experiment showed that our system's performance is F1 = 68.58%. This means that state-of-the-art system can be developed with our technique. It is expected that future work that enables the system to utilize semantic information can lead to a significant performance improvement.