• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.1090-1100
• /
• 2024

While the incorporating ESG indicator is recognized as crucial for sustainability and increased firm value, inconsistent disclosure of ESG data and vague assessment standards have been key challenges. To address these issues, this study proposes an ambiguous text-based automated ESG rating strategy. Earnings Call Transcript data were classified as E, S, or G using the Refinitiv-Sustainable Leadership Monitor's over 450 metrics. The study employed advanced natural language processing techniques such as BERT, RoBERTa, ALBERT, FinBERT, and ELECTRA models to precisely classify ESG documents. In addition, the authors computed the average predicted probabilities for each label, providing a means to identify the relative significance of different ESG factors. The results of experiments demonstrated the capability of the proposed methodology in enhancing ESG assessment criteria established by various rating agencies and highlighted that companies primarily focus on governance factors. In other words, companies were making efforts to strengthen their governance framework. In conclusion, this framework enables sustainable and responsible business by providing insight into the ESG information contained in Earnings Call Transcript data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2178-2198
• /
• 2024

Graph-based document models have good capabilities to reveal inter-dependencies among unstructured text data. Natural language processing (NLP) systems that use such models as an intermediate representation have shown good performance. This paper proposes a novel fuzzy graph-based document model and to demonstrate its effectiveness by applying fuzzy logic tools for text summarization. The proposed system accepts a text document as input and identifies some of its sentence level features, namely sentence position, sentence length, numerical data, thematic word, proper noun, title feature, upper case feature, and sentence similarity. The fuzzy membership value of each feature is computed from the sentences. We also propose a novel algorithm to construct the fuzzy graph as an intermediate representation of the input document. The Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metric is used to evaluate the model. The evaluation based on different quality metrics was also performed to verify the effectiveness of the model. The ANOVA test confirms the hypothesis that the proposed model improves the summarizer performance by 10% when compared with the state-of-the-art summarizers employing alternate intermediate representations for the input text.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1121-1128
• /
• 2024

Prominent general contractors (GCs) in Japan have historically maintained dedicated research and development (R&D) institutes that conduct comprehensive studies on structural engineering, construction techniques, and environmental management technologies. These research endeavors have evolved over time, reflecting the prevailing conditions and trends in the construction industry during each era. We examined changes in R&D activities over the past decade by analyzing R&D descriptions and statistical data contained in securities reports issued by 14 leading GCs using natural language processing. Our analysis revealed that over the course of the decade, R&D activities transformed significantly due to market dynamics and macro-environmental factors. For instance, during the 2000s, a surge in demand for high-rise condominium buildings led to an increased presence of related terminology in the 2009 fiscal year (FY) securities reports. However, this trend had declined by FY 2019. Notably, in FY 2019, there was an observable increase in R&D efforts concerning wood and cross-laminated timber applications. This can be attributed to the enforcement of laws and standardization measures that facilitated the proliferation of wood-based construction techniques in the 2010s. Throughout the 2010s, the primary concern of the Japanese construction industry was optimizing production processes to meet escalating domestic construction demands. A comparative analysis between 2009 and 2019 indicates a shift in focus, with fewer references to product innovation and a more pronounced emphasis on process innovation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2049-2068
• /
• 2021

AI combined with NLP techniques has promoted the use of Virtual Assistants and have made people rely on them for many diverse uses. Conversational Agents are the most promising technique that assists computer users through their operation. An important challenge in developing Conversational Agents globally is transferring the groundbreaking expertise obtained in English to other languages. AI is making it possible to transfer this learning. There is a dire need to develop systems that understand secular languages. One such difficult language is Hindi, which is the fourth most spoken language in the world. Semantic similarity is an important part of Natural Language Processing, which involves applications such as ontology learning and information extraction, for developing conversational agents. Most of the research is concentrated on English and other European languages. This paper presents a Corpus-based word semantic similarity measure for Hindi. An experiment involving the translation of the English benchmark dataset to Hindi is performed, investigating the incorporation of the corpus, with human and machine similarity ratings. A significant correlation to the human intuition and the algorithm ratings has been calculated for analyzing the accuracy of the proposed similarity measures. The method can be adapted in various applications of word semantic similarity or module for any other language.

• KNOM Review
• /
• v.24 no.2
• /
• pp.35-47
• /
• 2021

Various stress exists in a modern society, which requires constant competition and improvement. A person under stress often shows his pressure in his facial expression and language. Therefore, it is possible to measure the pressure using facial expression and language analysis. The paper proposes a stress measurement system using facial expression and language sensitivity analysis. The method analyzes the person's facial expression and language sensibility to derive the stress index based on the main emotional value and derives the integrated stress index based on the consistency of facial expression and language. The quantification and generalization of stress measurement enables many researchers to evaluate the stress index objectively in general.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.11-22
• /
• 2023

This research aimed to examine the public's perception of the "rate of sentence reduction for reasons of mental and physical weakness" and investigate if it aligns with the actual practice. Various sources, such as the Supreme Court's Courtnet search system, the number of mental evaluation requests, and the number of articles and comments related to "mental weakness" on Naver News were utilized for the analysis. The findings indicate that the public has a negative opinion on reducing sentences due to mental and physical weakness, and they are dissatisfied with the vagueness of the standards. However, this study also confirms that the court strictly applies the reduction of responsibility for individuals with mental disabilities specified in Article 10 of the Criminal Act based on the analysis of actual judgments and the number of requests for psychiatric evaluation. In other words, even though the recognition of perpetrators' mental disorders is declining, the public does not seem to recognize this trend. This creates a negative impact on the public's trust in state institutions. Therefore, law enforcement agencies, such as the police and prosecutors, need to enforce the law according to clear standards to gain public trust. The judiciary also needs to make a firm decision on commuting sentences for mentally and physically infirm individuals and inform the public of the outcomes of its application.

• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.573-575
• /
• 2019

현존하는 음악 추천형 챗봇들은 사용자의 의도가 아닌 챗봇 임의의 분류기준을 가지고 음악을 추천해왔다. 하지만 이러한 음악 추천은 공급자의 의도에 제한되어있는 단면적인 추천이 될 가능성이 높다. 이를 개선하고자 본 논문에서는 자연어를 처리하는 기법(NLP)의 처리를 통해 추출한 단어를 자연어 이해 기법(NLU)으로 특정 감성어 데이터를 마이닝하는 방법을 채용한다. 이를 통해 추출된 감성어를 원하는 쿼리에 따라 매핑된 음악데이터만을 추출한다. 이를 통해 닫힌 대화 구조에서의 사용자 의도 해석의 한계를 극복한다.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.1014-1017
• /
• 2020

Many natural language processing (NLP) models utilize pre-trained word embeddings to leverage latent information. One of the most successful word embedding model is the Skip-gram (SG). In this paper, we propose a Skipgram drop (SG-Drop) model, which is a variation of the SG model. The SG-Drop model is designed to reduce training time efficiently. Furthermore, the SG-Drop allows controlling training time with its hyperparameter. It could train word embedding faster than reducing training epochs while better preserving the quality.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.297-299
• /
• 2021

Text classification is one of the popular tasks in Natural Language Processing (NLP) used to classify text or document applications such as sentiment analysis and email filtering. Nowadays, state-of-the-art (SOTA) Machine Learning (ML) and Deep Learning (DL) algorithms are the core engine used to perform these classification tasks with high accuracy, and they show satisfying results. This paper conducts a benchmarking performance's analysis of multiple SOTA algorithms on the first known labeled Korean voice phishing dataset called KorCCVi. Experimental results reveal performed on a test set of 366 samples reveal which algorithm performs the best considering the training time and metrics such as accuracy and F1 score.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.932-933
• /
• 2023

이 연구는 사람의 감정 변화를 건강하게 파악하고 분석하기 위해 시작되었다. Natural Language Processing(NLP)는 컴퓨터가 인간의 언어를 이해하기 위해 개발된 자연어 처리 기술이다. 본 논문에서는 이 기술을 이용하여 Text Mining을 통해 사용자가 작성한 일기에 담긴 감정을 분석하고 LSTM 모델과 GRU 모델을 비교군으로 두어 두 모델 중 감정 분석에 더 적합한 모델을 찾는 과정을 거쳤다. 이 과정을 정확도가 더 높은 LSTM 모델을 사용하여 감정 분석 결과를 분류하였다.