• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1081-1089
• /
• 2014

Context-sensitive spelling-error correction methods are largely classified into rule-based methods and statistical data-based methods, the latter of which is often preferred in research. Statistical error correction methods consider context-sensitive spelling error problems as word-sense disambiguation problems. The method divides a vocabulary pair, for correction, which consists of a correction target vocabulary and a replacement candidate vocabulary, according to the context. The present paper proposes a method that integrates a word-phrase n-gram model into a conventional model in order to improve the performance of the probability model by using a correction vocabulary pair, which was a result of a previous study performed by this research team. The integrated model suggested in this paper includes a method used to interpolate the probability of a sentence calculated through each model and a method used to apply the models, when both methods are sequentially applied. Both aforementioned types of integrated models exhibit relatively high accuracy and reproducibility when compared to conventional models or to a model that uses only an n-gram.

• Journal of KIISE:Databases
• /
• v.36 no.4
• /
• pp.254-262
• /
• 2009

As the trend of e-business activities develop, customers come into contact with products through on-line shopping sites and lots of customers refer product reviews before the purchasing on-line. However, as the volume of product reviews grow, it takes a great deal of time and effort for customers to read and evaluate voluminous product reviews. Lately, attention is being paid to Opinion Mining(OM) as one of the effective solutions to this problem. In this paper, we propose an efficient method for opinion sentiment classification of product reviews using product specific context information of words occurred in the reviews. We define the context information of words and propose the application of context for sentiment classification and we show the performance of our method through the experiments. Additionally, in case of word corpus construction, we propose the method to construct word corpus automatically using the review texts and review scores in order to prevent traditional manual process. In consequence, we can easily get exact sentiment polarities of opinion words in product reviews.

• The Journal of Information Systems
• /
• v.24 no.1
• /
• pp.1-25
• /
• 2015

Social Network Service (SNS) has been played an important role in the life with the expansion of the modern technology in the cellular communication. More knowledge and understanding should be inevitable even if companies have taken advantage of SNS through word of mouth as one of the new paradigm. In most cases the crucial benefit or peculiarity of SNS has been overlooked because only general aspects of SNS have been applied in the online situation. As a result of this, same paradigm has been considered in reality as SNS was just used one of the marketing tools. However, essential aspects of SNS were investigated to see the relation of usage intention and word of mouth in this study. The hypothesis of the effect of continuous intention of the usage, trust and word of mouth was made and reviewed statistically. The statistical analysis showed there was significant among relationship, context, perceived service quality and continuous intention of the usage. In addition to that, self-expression, relationship, perceived service quality and trust were significant. Finally the continuous intention of the usage and word of mouth was significant as well. Based on this study, SNS provided by the companies could be effective to the customers in terms of word of mouth while different trend was shown in terms of trust.

• Journal of Digital Convergence
• /
• v.12 no.8
• /
• pp.147-155
• /
• 2014

Social commerce is a combination of social media and shopping. Social commerce, based on Web 2.0 technologies, has the various potentials, which is the factor attracting customers. In Korea, collegians are more active user of social media, in turn, are estimated more active customer in social commerce context. Present research explored what made Korean collegians use social commerce with extending technology acceptance model(TAM) with word-of-mouth(WOM) and perceived enjoyment(PE). We found that WOM affected indirectly the intention to use(ITU) with mediating PE, in turn, PE has a positive effect on the all of constructs in TAM. Accordingly, TAM extended with WOM and PE is validated in social commerce context. Finally, based on the findings, implications and suggestions for future studies are discussed.

• The Korean Journal of Franchise Management
• /
• v.13 no.4
• /
• pp.13-22
• /
• 2022

Purpose: Brand hearsay refers to information that can be acquired from advertisement, media publicity, and word-of-mouth prior to experiencing products or services of brands. Previous information about brands obtained through brand hearsay affects consumer behavior in choosing brands. Moreover, brand hearsay is an effective communication method in promoting brands to consumers. Thus, bakery franchises need to improve strengths and differentiate characteristics of their brand, thereby attracting more consumers. Therefore, this study investigates relationships the effect of brand hearsay on consumers' brand attitude and brand loyalty in the context of franchised bakery brands. Research design, data, and methodology: A research model was proposed to examine structural relationships between brand hearsay (advertising, publicity, word-of-mouth), brand attitude, and brand loyalty. An online survey was conducted to consumers who had an experience of visiting a franchise bakery. A total of 513 responses were used for data analysis. SPSS 22.0 was used for analyzing general demographics, and SmartPLS 4.0 was used to test validity and reliability of the proposed model. Result: Among attributes of brand hearsay, advertisement and word-of-mouth had positively significant effects on brand attitude, but no significant effect was found between publicity and attitude. Advertisement had a positively significant impact on brand loyalty, while publicity had a negative effect on brand loyalty opposite to hypothesis. Moreover, brand attitude had a statistically significant effect on brand loyalty. Conclusions: In the context of franchise bakeries, brand hearsay contents may change consumers' attitude toward brands but does not increase brand loyalty. Though media publicity does not affect consumers' attitude toward brands, it may decrease brand loyalty when consumers are too exposed to it. In addition, it is necessary to enhance brand attitude to increase brand loyalty of customers. This study provides bakery franchisors and franchisees information about which type of brand hearsay (e.g., advertisement, word-of-mouth, media, publicity) is effective in enhancing brand attitudes and loyalty of consumers. Further studies may include other variables (e.g., trust) in addition to attitude and loyalty, or compare findings based on brand characteristics (e.g., low-to-medium/high prices, store size).

• The Journal of Bigdata
• /
• v.3 no.1
• /
• pp.13-20
• /
• 2018

Stock market prediction has been long dream for researchers as well as the public. Forecasting ever-changing stock market, though, proved a Herculean task. This study proposes a novel stock market sentiment lexicon acquisition system that can predict the growth (or decline) of stock market index, based on economic news. For this purpose, we have collected 3-year's economic news from January 2015 to December 2017 and adopted Word2Vec model to consider the context of words. To evaluate the result, we performed sentiment analysis to collected news data with the automated constructed lexicon and compared with closings of the KOSPI (Korea Composite Stock Price Index), the South Korean stock market index based on economic news.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.24-29
• /
• 2018

Text analysis technique for natural language processing in deep learning represents words in vector form through word embedding. In this paper, we propose a method of constructing a document vector and classifying it into spam and normal text message, using word embedding and deep learning method. Automatic spacing applied in the preprocessing process ensures that words with similar context are adjacently represented in vector space. Additionally, the intentional word formation errors with non-alphabetic or extraordinary characters are designed to avoid being blocked by spam message filter. Two embedding algorithms, CBOW and skip grams, are used to produce the sentence vector and the performance and the accuracy of deep learning based spam filter model are measured by comparing to those of SVM Light.

• Journal of Science Education
• /
• v.46 no.1
• /
• pp.17-29
• /
• 2022

The purpose of this study is to look qualitatively into how efficiently and reasonably a computer can learn themes related to the Nature of Science (NOS). In this regard, a corpus has been constructed focusing on literature (920 abstracts) related to NOS, and factors of the optimized Word2Vec (CBOW, Skip-gram) were confirmed. According to the four dimensions (Inquiry, Thinking, Knowledge and STS) of NOS, the comparative evaluation on the word-level word embedding was conducted. As a result of the study, according to the previous studies and the pre-evaluation on performance, the CBOW model was determined to be 200 for the dimension, five for the number of threads, ten for the minimum frequency, 100 for the number of repetition and one for the context range. And the Skip-gram model was determined to be 200 for the number of dimension, five for the number of threads, ten for the minimum frequency, 200 for the number of repetition and three for the context range. The Skip-gram had better performance in the dimension of Inquiry in terms of types of words with high similarity by model, which was checked by applying it to the four dimensions of NOS. In the dimensions of Thinking and Knowledge, there was no difference in the embedding performance of both models, but in case of words with high similarity for each model, they are sharing the name of a reciprocal domain so it seems that it is required to apply other models additionally in order to learn properly. It was evaluated that the dimension of STS also had the embedding performance that was not sufficient to look into comprehensive STS elements, while listing words related to solution of problems excessively. It is expected that overall implications on models available for science education and utilization of artificial intelligence could be given by making a computer learn themes related to NOS through this study.

• Proceedings of the KSPS conference
• /
• 1997.07a
• /
• pp.81-91
• /
• 1997

This paper deals with the problems of English listening comprehension: the rate of understanding difference in positions and sentence structures, parts of speech easily missed to understand, English sounds only in English(not in Korean), confusion of sounds, unaccented prefixes and suffixes, polysemy, homonym, juncture, understanding as one word by two different words, and sound blending in a normal speed of connected speech. Bearing those in mind I taught Suwon University freshmen video English with the mixed idea of Peterson's bottom-up and top-down methods putting in a meaningful context with thought group rather than word to word understanding. As a consequence, their errors come: prepositions, conjunctions, unstressed prefixes and suffixes, -ing from the present progressives and so forth. Assignments to have students transcribe the TV commercials and the names of reporters or Korean related news from English broadcastings are of use and help.

• Asia pacific journal of information systems
• /
• v.25 no.4
• /
• pp.805-822
• /
• 2015

Online communities are an important source of electronic word-of-mouth (e-WOM). However, few studies have examined the use of such messages within the Middle Eastern context. This study focuses on Saudi women as members of an online beauty forum. Previous work suggested a mediating effect of gender, with women being more likely to trust word-of-mouth and follow it up with a purchase. A conceptual model with a theoretical underpinning from existing contributions in literature provides the basis of a coding framework for the message characteristics that influence members' e-WOM adoption. A total of 310 threads and 2200 messages coded into 5725 units were content analyzed to demonstrate cases where e-WOM was adopted and indicate further continuance intention with members returning to the forum. A new category of 'community bonding' was created from the content analysis given the prevalence of emotional aspects in messages. Emotion expressed in messages, often expressed in religious terms, is as influential and important as the cognitive aspects of community bonding.