• 한국정보시스템학회지:정보시스템연구
• /
• 제31권4호
• /
• pp.01-23
• /
• 2022

Purpose This study aims to propose a deep learning-based fake review detection model by combining authors' linguistic features and semantic information of reviews. Design/methodology/approach This study used 358,071 review data of Yelp to develop fake review detection model. We employed linguistic inquiry and word count (LIWC) to extract 24 linguistic features of authors. Then we used deep learning architectures such as multilayer perceptron(MLP), long short-term memory(LSTM) and transformer to learn linguistic features and semantic features for fake review detection. Findings The results of our study show that detection models using both linguistic and semantic features outperformed other models using single type of features. In addition, this study confirmed that differences in linguistic features between fake reviewer and authentic reviewer are significant. That is, we found that linguistic features complement semantic information of reviews and further enhance predictive power of fake detection model.

• ETRI Journal
• /
• 제32권3호
• /
• pp.482-485
• /
• 2010

Feature selection is very important for feature-based relation classification tasks. While most of the existing works on feature selection rely on linguistic information acquired using parsers, this letter proposes new features, including probabilistic and semantic relatedness features, to manifest the relatedness between patterns and certain relation types in an explicit way. The impact of each feature set is evaluated using both a chi-square estimator and a performance evaluation. The experiments show that the impact of relatedness features is superior to existing well-known linguistic features, and the contribution of relatedness features cannot be substituted using other normally used linguistic feature sets.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권11호
• /
• pp.541-548
• /
• 2016

사용자의 다양한 의견을 수렴하고 모니터링하기 위한 정보원으로써 소셜미디어의 활용은 이미 필수가 되었다. 본 논문은 소셜미디어에 나타난 다양한 이슈 중 여론 형성에 악영향을 끼치는 부정적 사건을 이슈 '리스크'로 정의, 그 세부 유형을 자동으로 분류하는 모델을 개발하고자 한다. 이를 위해 소셜미디어에 나타난 다양한 어휘 자질을 선별, 그 효과를 규명하였다. 특히 리스크 문장의 어휘 구문 특징을 표현하기 위한 자질로 워드 임베딩 학습 결과를 활용한다. 개별 어휘 자질의 특징을 분석하기 위해 언어분석 오류를 보정한 환경에서 수행한 실험 결과, 가장 효과가 큰 자질은 개체명 자질로 분석되었으며, 기본 어휘 자질을 기반으로 주요 술부의 워드 임베딩 결과와 워드 클러스터 결과를 모두 조합한 경우가 최고 성능을 보이는 것으로 파악되었다. 실제 소셜빅데이터에 적용하는 환경과 유사하도록 자동 언어분석 결과의 오류를 포함한 조건에서 실험한 결과, 고빈도 평가셋에서는 92.08%의 성능을, 전체 58개 범주 평가셋에서는 85.84%의 성능을 얻었다.

• 영어영문학
• /
• 제56권6호
• /
• pp.1163-1190
• /
• 2010

Korean EFL learners' stylistic sensitivity was examined through the two types of letter writing, professional and personal. The base of comparison with the English native speakers' stylistic sensitivity was the linguistic style markers that were statistically found by Biber's (1988) multi-dimensional model of variation of English language. The main finding was that Korean university students were sensitive to stylistic difference in the correct direction, though their linguistic repertoire was limited to the easy and simple linguistic features. Also, the learners were skewed in the involved style in both types of the letters unlike the native speakers and it was interpreted as due to the general developmental direction from informal to formal linguistic style. Learners were also skewed in the explicit style in both types of letters unlike the native speakers and it was interpreted as due to the learners' heavy reliance on one particular linguistic feature. As a whole, the learners' stylistic sensitivity heavily relied on the small number of linguistic features that they have already acquired, which happen to be simple and basic linguistic features.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 컴퓨터소사이어티 추계학술대회논문집
• /
• pp.227-230
• /
• 2003

We can not distinguish semantism of the feature of the current language “big”, “small”, “beautiful”. But we study artificial linguistic interface work and convert natural language to digital binary linguistic theory, we should define the basical conversion process. When we utilize the sum of product fuzzy theory and the visible numerical value, we can establish reasoning rule of input language. Fuzzy theory should be converted to general resulting rule.

• Journal of Smart Tourism
• /
• 제1권3호
• /
• pp.21-29
• /
• 2021

This study explored the relationship between post types and linguistic characteristics in marketer-generated content and social media engagement to find the optimized content to enhance social media engagement level. Post data of 23,588 marketer-generated content were collected from 50 states' destination marketing organization Facebook pages in the United States. The collected data were analyzed by employing social media analytics, linguistic analysis, multivariate analysis of variance, and discriminant analysis. The results showed that there are significant differences in both engagement indicators and linguistic scores among the three post types. Based on research findings, this research not only provided researchers with theoretical implications but also suggested practitioners the most effective content designs for travel destination marketing in Facebook.

• 인지과학
• /
• 제2권1호
• /
• pp.143-165
• /
• 1990

I will discuss some aspects of the meaning of prodiscoure maker 'kulay'in Korea.This marker has been studied few scholars,since Korean lingusts did not have any interest about this category of linguistic form.Also,they did not realized the importance of discourse and discourse markers.So,we have only shallow information about prodiscourse phenomena and prodiscourse markers,too. Morphologically,kulay(그래)'could be analyzed into 'ku(그)'and 'lay(래)'and 'lay(래)'could be divided into'l(ㄹ)'and 'ay(ㅐ)' again.But I will discuss 'kulay'as one linguistic unit without divison. It will be claimed in this paper that both [prodiscoures]feature and [discourse continuity]feature can satisfactorily account for the core meaning of'kulay'.And,it will be mentioned that the marker has many kinds of specfic meaning depends on paricular discourse.Also, I would like to examine the semantic feature([prodiscourse+discourse continuity]) in many kinds of korean discourse.And I will show that some factors re;ated tp the marker's specific meaning are the meaning of preceding and following discourse and the participant's psychological attitude.The conclusion must be that the meaning of 'kulay'can help us understand certain phenomena about prodiscourse and prodiscourse markers in the korean language.Also the various meanings of 'kulay'can give more information to Applied-Korean linguistics.

• International Journal of Internet, Broadcasting and Communication
• /
• 제7권2호
• /
• pp.142-148
• /
• 2015

The main purpose of this squib is to provide a new principled account for variation of canonical sentence structure in Korean and Japanese based on the linguistic data commonly observed in some dialects of Korean and Japanese. Unlike the English case in which Comp(lementizer) such as 'that' in an embedded clause freely drops as far as the ECP (Lasnik & Saito 1992) is obeyed, some dialects of both Korean and Japanese show interesting linguistic data very different from those of English, thereby leading us to reasonably doubt the traditionally-accepted paradigm of the canonical sentence structure of CP for all languages. In this squib I propose, based on Korean & Japanese dialects and by developing the Minimal Structure Principle (MSP) ($Bo{\check{s}}kovi{\acute{c}}$ 1997, p. 25), that the cannonical structure of a sentence is not fixed, from the beginning at all, to be one single maximal category, CP. Instead, it should be decided to be either CP or IP, based on the feature of [${\pm}$markedness] and MSP, and the marked (or non-cannonical) embedded sentence needs to satisfy ECP for adjacency (or feature-licensing by the matrix verb in the MP terminology).

• 영어어문교육
• /
• 제9권1호
• /
• pp.23-48
• /
• 2003

This paper provides an analysis of the linear constituent order of the NP in three different types of languages based on 33 languages: the NP with the prenominal modifiers, the NP with the postnominal modifiers, and the NP with both prenominal and postnominal modifiers (the mixed NP). Languages have NPs that feature different linear order, of the NP constituents. We attribute such different linear constituent orders within the NP to the linguistic distance and the limits imposed by the constituency and adjacency. We use the various kinds of alignment constraints which properly reflect the linguistic distance between the noun and each constituent. Language universals on word order provide us some general orders of various NP constituents. If we adopt the linguistic distance, the limits imposed by the constituency and the adjacency, and the alignment constraints, we can explain the complicated differences of NP constituent orders of languages of the world.

• 인문언어
• /
• 제1권2호
• /
• pp.123-139
• /
• 2001

In the history of linguistics in the world the scholars in India could be regarded as the representative linguists, who had provided the cornerstone of the academic development at linguistics. Without looking into the contents of Indian linguistic theories devised and developed in the past it would be almost impossible to account for the origin of descriptive linguistics and historical linguistics. These linguistics trends became full-fledged in 19 and 20 century and are still accepted by a lot of researchers in order to analyze newly revealed languages and train students only coming up the toddling level of linguistic studies. In this paper I will show how far the influence of Indian linguistics has colored the flow of linguistic growth historically. Especially through the analysis of Panini grammar I will prove the intimate relationship between the Indian linguistic theory and the generative grammar - it is the most active theory at present. The methods that Panini applied to constitute the rules like sutra include lots of information, that also could be discovered at the rules postulated in the generative grammar. One of the common features found at both linguistic theories is the simplicity of rule representation. At the generative grammar a rule has to be established without any redundancy. When certain number of sounds like p, b, m show the same phonological. change relevant to lips (labial in linguistic term) different rules need not to be given for each sound separately. It is better to find a way of putting the sounds together in a rule with grouping the 3 sounds with the shared phonetic feature 'labial'. In Panini grammar the form of a rule was decided based on the simplicity, too. For example, sutra 6.1.77 shows the phonological connection between the vowels i, u r 1 and the semi-vowels y, v, r, 1. However, it does not require to postulate 4 individual rules respectively. Instead a rule in which the vowels and the semi-vowels are involved is suggested, and linguistically the rule make it clear that the more simpler the rules will be the better they can reflect the efficiency of human language acquisition. Although the systems introduced at Panini grammar have some sense of distance from the language education itself we cannot deny the fact that the grammar formulates the a turning point of linguistic development. It is essential for us to think over the grammar from the view point of the modem linguistic theories to understand their root and trunk more thoroughly. It will also help us to predict in which way linguistic tendency will proceed to in future.