• Journal of KIISE:Software and Applications
• /
• v.37 no.12
• /
• pp.946-950
• /
• 2010

Many sentiment categorization systems based on machine learning methods use morphological analyzers in order to extract linguistic features from sentences. However, the morphological analyzers do not generally perform well in a customer review domain because online customer reviews include many spacing errors and spelling errors. These low performances of the underlying systems lead to performance decreases of the sentiment categorization systems. To resolve this problem, we propose a feature extraction method based on simple longest matching of Eojeol (a Korean spacing unit) and phoneme patterns. The two kinds of patterns are automatically constructed from a large amount of POS (part-of-speech) tagged corpus. Eojeol patterns consist of Eojeols including content words such as nouns and verbs. Phoneme patterns consist of leading consonant and vowel pairs of predicate words such as verbs and adjectives because spelling errors seldom occur in leading consonants and vowels. To evaluate the proposed method, we implemented a sentiment categorization system using a SVM (Support Vector Machine) as a machine learner. In the experiment with Korean customer reviews, the sentiment categorization system using the proposed method outperformed that using a morphological analyzer as a feature extractor.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.116-122
• /
• 2023

Sentiment categorization technique be commonly isolated interested in threes significant classifications name Machine Learning Procedure (ML), Lexicon Based Method (LB) also finally, the Hybrid Method. In Machine Learning Methods (ML) utilizes phonetic highlights with apply notable ML algorithm. In this paper, in classification and identification be complete base under in optimizations technique called sequential minimal optimization with Random Forest algorithm (SMORF) for expanding the exhibition and proficiency of sentiment classification framework. The three existing classification algorithms are compared with proposed SMORF algorithm. Imitation result within experiential structure is Precisions (P), recalls (R), F-measures (F) and accuracy metric. The proposed sequential minimal optimization with Random Forest (SMORF) provides the great accuracy.

• Journal of information and communication convergence engineering
• /
• v.16 no.2
• /
• pp.106-113
• /
• 2018

Although deep learning methods of convolutional neural networks (CNNs) and long-/short-term memory (LSTM) are widely used for text categorization, they still have certain shortcomings. CNNs require that the text retain some order, that the pooling lengths be identical, and that collateral analysis is impossible; In case of LSTM, it requires the unidirectional operation and the inputs/outputs are very complex. Against these problems, we thus improved these traditional deep learning methods in the following ways: We created collateral CNNs accepting disorder and variable-length pooling, and we removed the input/output gates when creating bidirectional LSTMs. We have used four benchmark datasets for topic and sentiment classification using the new methods that we propose. The best results were obtained by combining LTSM regional embeddings with data convolution. Our method is better than all previous methods (including deep learning methods) in terms of topic and sentiment classification.

• ETRI Journal
• /
• v.38 no.3
• /
• pp.494-501
• /
• 2016

Sentiment analysis incorporates natural language processing and artificial intelligence and has evolved as an important research area. Sentiment analysis on product reviews has been used in widespread applications to improve customer retention and business processes. In this paper, we propose a method for performing an intensified sentiment analysis on customer product reviews. The method involves the extraction of two feature sets from each of the given customer product reviews, a set of acoustic features (representing emotions) and a set of lexical features (representing sentiments). These sets are then combined and used in a supervised classifier to predict the sentiments of customers. We use an audio speech dataset prepared from Amazon product reviews and downloaded from the YouTube portal for the purposes of our experimental evaluations.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.238-246
• /
• 2021

The rapid rise of the Internet and social media has resulted in a large number of text-based reviews being placed on sites such as social media. In the age of social media, utilizing machine learning technologies to analyze the emotional context of comments aids in the understanding of QoS for any product or service. The classification and analysis of user reviews aids in the improvement of QoS. (Quality of Services). Machine Learning algorithms have evolved into a powerful tool for analyzing user sentiment. Unlike traditional categorization models, which are based on a set of rules. In sentiment categorization, Bidirectional Long Short-Term Memory (BiLSTM) has shown significant results, and Convolution Neural Network (CNN) has shown promising results. Using convolutions and pooling layers, CNN can successfully extract local information. BiLSTM uses dual LSTM orientations to increase the amount of background knowledge available to deep learning models. The suggested hybrid model combines the benefits of these two deep learning-based algorithms. The data source for analysis and classification was user reviews of Indian Railway Services on Twitter. The suggested hybrid model uses the Keras Embedding technique as an input source. The suggested model takes in data and generates lower-dimensional characteristics that result in a categorization result. The suggested hybrid model's performance was compared using Keras and Word2Vec, and the proposed model showed a significant improvement in response with an accuracy of 95.19 percent.

• Journal of Internet Computing and Services
• /
• v.19 no.1
• /
• pp.155-166
• /
• 2018

These days, online media, such as blogospheres, online communities, and social networking sites, provides the uncountable user-generated content (UGC) to discover market intelligence and business insight with. The business has been interested in consumers, and constantly requires the approach to identify consumers' opinions and competitive advantage in the competing market. Analyzing consumers' opinion about oneself and rivals can help decision makers to gain in-depth and fine-grained understanding on the human and social behavioral dynamics underlying the competition. In order to accomplish the comparison study for rival products and companies, we attempted to do competitive analysis using text mining with online UGC for two popular and competing ramens, a market leader and a market follower, in the Korean instant noodle market. Furthermore, to overcome the lack of the Korean sentiment lexicon, we developed the domain specific sentiment dictionary of Korean texts. We gathered 19,386 pieces of blogs and forum messages, developed the Korean sentiment dictionary, and defined the taxonomy for categorization. In the context of our study, we employed sentiment analysis to present consumers' opinion and statistical analysis to demonstrate the differences between the competitors. Our results show that the sentiment portrayed by the text mining clearly differentiate the two rival noodles and convincingly confirm that one is a market leader and the other is a follower. In this regard, we expect this comparison can help business decision makers to understand rich in-depth competitive intelligence hidden in the social media.

• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.151-154
• /
• 2009

인터넷이 크게 발전하면서 현재는 인터넷으로 쉽게 쇼핑을 할 수 있다. 이 때 물건의 구입에 큰 영향력을 미치는 것이 바로 그 물건의 상품평이다. 하지만 실제로 수많은 상품평을 사용자가 일일이 확인하고 판단하는 데에는 많은 시간이 소모된다. 이러한 문제점을 해결하기 위해서 본 논문에서는 상품평 문장을 일반, 긍정, 부정의 세 단계로 나누는 시스템을 제안한다. 감정을 판단하는데 중요한 역할을 하는 품사에 따라 우선순위를 달리하여 자질을 추출한다. 추출된 자질을 사용하여 Paul Graham을 사용하여 가중치를 계산하고 기계학습을 한다. 실험은 일반과 감정(긍정, 부정)으로 분류하는 실험과 긍정과 부정으로 분류하는 실험을 하였다. 실험 결과 품사에 우선순위를 사용하여 만든 시스템이 기본 시스템보다 더 적은 자질을 사용하고 더 높은 성능을 보였다.

• Korean Journal of Legislative Studies
• /
• v.23 no.1
• /
• pp.113-149
• /
• 2017

This study aims to identify the micro-level, social psychological foundation of regionalism and analyze its change and continuity by comparing 1988, 2003, and 2016 survey results. Drawing on the theory of prejudice and social identity, it clarifies the concept of regionalism and examines its affective, behavioral, cognitive implications. In the empirical analysis, where it takes advantage of relevant questions of the same or similar wording in three nationally representative surveys, the study identifies the changes in regionalism at the individual level focusing on anti-Honam prejudice and discrimination and attribution of regional conflict. First, anti-Honam prejudice has been in decline nationally as well as regardless of where one has grown up, except for Daegu/Kyungpook area. Second, anti-Honam prejudice has been weakened among younger generations while regional party identification now affects the sentiment in the direction of regional cleavage overlapped with ideological leanings. Third, while most respondents do not experience explicit discrimination, Honam natives are still more likely to experience discrimination, especially identity and self-esteem related, due to his or her home town. Fourth, Honam natives have been more likely to attribute regional conflict to an external, structural factor like government economic policy and less likely to a subjective one like regional sentiment, which seems to be consistent with attributional attitudes of the victims of prejudice. The study ends with the discussion of how to reduce further anti-Honam prejudice, which includes contact hypothesis, recategorization, cross-categorization, and de-categorization.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.113-123
• /
• 2024

Stock market news sentiment analysis (SA) aims to identify the attitudes of the news of the stock on the official platforms toward companies' stocks. It supports making the right decision in investing or analysts' evaluation. However, the research on Arabic SA is limited compared to that on English SA due to the complexity and limited corpora of the Arabic language. This paper develops a model of sentiment classification to predict the polarity of Arabic stock news in microblogs. Also, it aims to extract the reasons which lead to polarity categorization as the main economic causes or aspects based on semantic unity. Therefore, this paper presents an Arabic SA approach based on the logistic regression model and the Bidirectional Encoder Representations from Transformers (BERT) model. The proposed model is used to classify articles as positive, negative, or neutral. It was trained on the basis of data collected from an official Saudi stock market article platform that was later preprocessed and labeled. Moreover, the economic reasons for the articles based on semantic unit, divided into seven economic aspects to highlight the polarity of the articles, were investigated. The supervised BERT model obtained 88% article classification accuracy based on SA, and the unsupervised mean Word2Vec encoder obtained 80% economic-aspect clustering accuracy. Predicting polarity classification on the Arabic stock market news and their economic reasons would provide valuable benefits to the stock SA field.

• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.58-62
• /
• 2008

인터넷 상에서 상품을 구입할 때 고려하는 부분 중의 하나가 상품평이다. 하지만 이러한 상품평들을 개인이 일일이 확인 하는데에는 상당한 시간이 소요된다. 이러한 문제점을 줄이기 위해서 본 논문에서는 인터넷 상의 상품평에 대한 의견을 긍정, 부정, 일반으로 나누는 시스템을 제안한다. 제안 시스템은 CRFs 기계학습모델을 기반으로 하며, 연결어미, 형태소 유니그램, 슬라이딩 윈도우 기법의 형태소 바이그램을 자질로 사용한다. 실험을 위해서 가격비교 사이트의 모니터 카테고리에서 561개의 상품평을 수집하였다. 이 중 465개의 상품평을 학습 문서로 사용하였고 96개의 상품평을 실험 문서로 사용하였다. 제안 시스템은 실험결과 79% 정도의 정확도를 보였다. 추가 실험으로 제안 시스템이 사람들과 얼마나 비슷한 성능을 보이는지 알아보기 위해서 카파 테스트를 실시하였다. 카파 테스트를 실시한 결과, 사람간의 카파 계수는 0.6415였으며, 제안 시스템과 사람 간의 카파 계수는 평균 0.5976이였다. 결론적으로 제안 시스템이 사람보다는 떨어지지만 유사한 정도의 성능을 보임을 알 수 있었다.