• The Journal of Information Systems
• /
• v.31 no.4
• /
• 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.

• Journal of English Language & Literature
• /
• v.56 no.6
• /
• 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.

• Korean Journal of English Language and Linguistics
• /
• v.4 no.1
• /
• pp.33-60
• /
• 2004

This study was an attempt to present an appropriate way of interpreting L2 learners' linguistic behavior within Universal Grammar (UG) framework. Based on the Korean EFL adult learners' performance on the Subjacency violation sentences, the study suggested that the EFL learners are able to acquire subtle knowledge of target grammar and their linguistic behavior should be interpreted with the most recent version of UG theory, the Minimalist Program (MP) notion. The MP notion seems more plausible to accommodate incomplete L2 grammar while acknowledging UG-constrained interlanguage which the previous version, Principles and Parameters (P&P) approach, could not explain very well. The study observed no age-effects among the Korean EFL learners in their linguistic competence measured by the performance on the UG-constraint violation sentences. Having suggested that the MP notion can be a more reasonable tool to explain the EFL learners' linguistic behavior, the study introduced comprehensive hypotheses such as Constructionist Model (CM) and the Ontogeny Phylogeny Model (OPM).

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.427-432
• /
• 2005

This paper is concerned with a simultaneous design of TSK (Takagi-Sugeno-Kang)-linguistic fuzzy models with uncertain model output and the computationally efficient representation. For this purpose, we use the fundamental idea of linguistic models introduced by Pedrycz and develop their comprehensive design framework. The design process consists of several main phases such as (a) the automatic generation of the linguistic contexts by probabilistic distribution using CDF (conditional density function) and PDF (probability density function) (b) performing context-based fuzzy clustering preserving homogeneity based on the concept of fuzzy granulation (c) augment of bias term to compensate bias error (d) combination of TSK and linguistic context in the consequent part. Finally, we contrast the performance of the enhanced models with other fuzzy models for automobile MPG predication data and coagulant dosing process in a water purification plant.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2010.05a
• /
• pp.60-65
• /
• 2010

Language learning involves linguistic environments around the learner. So the variation in training input to which the learner is exposed has been linked to their language learning. We explore how linguistic experiences can cause differences in learning linguistic structural features, as investigate in a probabilistic graphical model. We manipulate the amounts of training input, composed of natural linguistic data from animation videos for children, from holistic (one-word expression) to compositional (two- to six-word one) gradually. The recognition and generation of sentences are a "probabilistic" constraint satisfaction process which is based on massively parallel DNA chemistry. Random sentence generation tasks succeed when networks begin with limited sentential lengths and vocabulary sizes and gradually expand with larger ones, like children's cognitive development in learning. This model supports the suggestion that variations in early linguistic environments with developmental steps may be useful for facilitating language acquisition.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1187-1190
• /
• 1993

The problem of the optimization of fuzzy relational models for dealing with (non-fuzzy) numerical data is investigated. In this context, interfaces optimization assumes particular importance, becoming a determinant factor in what concerns the overall model performance. Considering this, several scenarios for building fuzzy relational models are presented. These are: (i) optimizing I/O interfaces in advance (independently from the linguistic part of the model); (ii) optimizing I/O interfaces in advance and allowing that their optimized parameters may change during the learning of the linguistic part of the model; (iii) build simultaneously both interfaces and the linguistic subsystem; and (iv) build simultaneously both linguistic subsystem and interfaces, now subject to semantic integrity constraints. As linguistic subsystems, both a basic type and an extended versions of fuzzy relation equations are exploited in each one of these scenarios. A comparative analysis of the differ nt approaches is summarized.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4952-4975
• /
• 2018

An induced hesitant linguistic aggregation operator is investigated in the paper, in which, hesitant fuzzy linguistic evaluation values are associated with probabilistic information. To deal with these hesitant fuzzy linguistic information, an induced hesitant fuzzy linguistic probabilistic ordered weighted averaging (IHFLPOWA) operator is proposed, monotonicity, boundary and idempotency of IHFLPOWA are proved. Then andness, orness and the entropy of dispersion of IHFLPOWA are analyzed, which are used to characterize the weighting vector of the operator, these properties show that IHFLPOWA is extensions of the induced linguistic ordered weighted averaging operator and linguistic probabilistic aggregation operator. In this paper, IHFLPOWA is utilized to gather linguistic information and create fuzzy ontologies, and a movie fuzzy ontology as an illustrative case study is used to show the elaboration of the proposed method and comparison with the existing linguistic aggregation operators, it seems that the IHFLPOWA operator is an useful and alternative operator for dealing with hesitant fuzzy linguistic information with probabilistic information.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1510-1515
• /
• 2005

This paper is concerned with a Logic-based Fuzzy Neural Networks (LFNN) with the aid of fuzzy granulation. As the underlying design tool guiding the development of the proposed LFNN, we concentrate on the context-based fuzzy clustering which builds information granules in the form of linguistic contexts as well as OR fuzzy neuron which is logic-driven processing unit realizing the composition operations of T-norm and S-norm. The design process comprises several main phases such as (a) defining context fuzzy sets in the output space, (b) completing context-based fuzzy clustering in each context, (c) aggregating OR fuzzy neuron into linguistic models, and (c) optimizing connections linking information granules and fuzzy neurons in the input and output spaces. The experimental examples are tested through two-dimensional nonlinear function. The obtained results reveal that the proposed model yields better performance in comparison with conventional linguistic model and other approaches.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.3
• /
• pp.55-62
• /
• 2018

In this paper, we propose a model to detect crowdfunding scams, which have been reportedly occurring over the last several years, based on their project information and linguistic features. To this end, we first collect and analyze crowdfunding scam projects, and then reveal which specific project-related information and linguistic features are particularly useful in distinguishing scam projects from non-scams. Our proposed model built with the selected features and Random Forest machine learning algorithm can successfully detect scam campaigns with 84.46% accuracy.

• Nuclear Engineering and Technology
• /
• v.53 no.11
• /
• pp.3675-3684
• /
• 2021

Human reliability analysis (HRA) is a proactive approach to model and evaluate human systematic errors, and has been extensively applied in various complicated systems. Dependence assessment among human errors plays a key role in the HRA, which relies heavily on the knowledge and experience of experts in real-world cases. Moreover, there are ofthen different types of uncertainty when experts use linguistic labels to evaluate the dependencies between human failure events. In this context, this paper aims to develop a new method based on linguistic hesitant fuzzy sets and the technique for human error rate prediction (THERP) technique to manage the dependence in HRA. This method handles the linguistic assessments given by experts according to the linguistic hesitant fuzzy sets, determines the weights of influential factors by an extended best-worst method, and confirms the degree of dependence between successive actions based on the THERP method. Finally, the effectiveness and practicality of the presented linguistic hesitant fuzzy THERP method are demonstrated through an empirical healthcare dependence analysis.