• Title/Summary/Keyword: GPT-3

Search Result 739, Processing Time 0.031 seconds

The Detection of Online Manipulated Reviews Using Machine Learning and GPT-3 (기계학습과 GPT3를 시용한 조작된 리뷰의 탐지)

  • Chernyaeva, Olga;Hong, Taeho
    • Journal of Intelligence and Information Systems
    • /
    • v.28 no.4
    • /
    • pp.347-364
    • /
    • 2022
  • Fraudulent companies or sellers strategically manipulate reviews to influence customers' purchase decisions; therefore, the reliability of reviews has become crucial for customer decision-making. Since customers increasingly rely on online reviews to search for more detailed information about products or services before purchasing, many researchers focus on detecting manipulated reviews. However, the main problem in detecting manipulated reviews is the difficulties with obtaining data with manipulated reviews to utilize machine learning techniques with sufficient data. Also, the number of manipulated reviews is insufficient compared with the number of non-manipulated reviews, so the class imbalance problem occurs. The class with fewer examples is under-represented and can hamper a model's accuracy, so machine learning methods suffer from the class imbalance problem and solving the class imbalance problem is important to build an accurate model for detecting manipulated reviews. Thus, we propose an OpenAI-based reviews generation model to solve the manipulated reviews imbalance problem, thereby enhancing the accuracy of manipulated reviews detection. In this research, we applied the novel autoregressive language model - GPT-3 to generate reviews based on manipulated reviews. Moreover, we found that applying GPT-3 model for oversampling manipulated reviews can recover a satisfactory portion of performance losses and shows better performance in classification (logit, decision tree, neural networks) than traditional oversampling models such as random oversampling and SMOTE.

Effect of Puerariae Radix Methanol Extract on Benzo(a)pyrenc -in - duced Hepatotoxicity in Rats (갈근 메탄올 엑기스가 흰쥐에 있어서 Benzo(a)pyrene에 의해 유도된 간장해에 미치 는 영향)

  • 이윤경
    • Journal of the East Asian Society of Dietary Life
    • /
    • v.4 no.2
    • /
    • pp.59-67
    • /
    • 1994
  • The present study was conducted to evaluate the hepatoprotective effect of puerariae Radix methanol extract on benzo(a) pyrene(B(a)P) - induced liver injuries in rats. In vitro experiment, primary cultured hepatocytes (5X105 cells/$m\ell$) were cultured for 20~24 hours after adding puerariae Radix mehtanol extract(32$\mu\textrm{g}$/$m\ell$) and B(a)P(50 uM). In vivo experiment, Puerariae Radix methanol extract(0.25 g/kg/day, per os) was administered for 7 days and B(a)P(0.1 mg/kg/day, intraperitoneally) was given after the last administration of extract. And then the hepatoprotective effect of Puerariae Radix methanol extract was investigated biochemically through in vitro and in vivo experiments. Namely, activities of enzymes (GOT, GPT and LDH) were measured and 3-(4,5-dimethylthiazol-2-yl)-2, 5-diphenyl tetrazolium bromide(MTT) assay were carried out in vitro cell culture study and GOT, GPT, LDH and ALP activities and HDL-cholesterol, total cholesterol and triglyceride contents were performed in vivo study. In vitro experiment, as a result of enzyme activity measurement(GOT, GPT and LDH) and MTT assay, GOT,GPT and LDH activities changed by B(a)P were recovered to normal levels and hepatocytes impaired by B(a)P were recovered to normal. In vivo experiment, Puerariae Radix methanol extract significantly decreased the enzyme activities(GOT, GPT, ALP and LDH in serum and GPT and ALP in tissue) and lipid contents in comparison to B(a)P-treated group.

A Study on Expression of NPC Colloquial Speech using Chat-GPT API in Games against Joseon Dynasty Settings (조선시대 배경의 게임에서 Chat-GPT API를 사용한 NPC 대화체 표현 연구)

  • Jin-Seok Lee;In-Chal Choi;Jung-Yi Kim
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.24 no.3
    • /
    • pp.157-162
    • /
    • 2024
  • This study was conducted to implement Joseon Dynasty conversational style using the ChatGPT API to enhance the immersion of games set in the Joseon era. The research focuses on interactions between middle-class players and other classes. Two methods were employed: learning the dialogues from historical dramas set in the Joseon Dynasty and learning the sentence endings typical of the period. The method of learning sentence endings was rated higher based on self-evaluation criteria. Reflecting this, prompts were constructed to represent NPC dialogues in the game settings of the Joseon era. Additionally, a method was proposed for creating various NPC prompts using prompt combination techniques. This study can serve as a reference for NPC dialogue creation in games set in the Joseon Dynasty.

A Study on the Correlation among the Patterns of the Zone 1, 2, 3 of Factor AA in 7-Zone-Diagnostic System and the Clinical Parameters (7구역진단기의 Factor AA 제1, 2, 3구역 유형과 임상지표와의 상관성 연구)

  • Cho, Yi-Hyun;Yu, Jung-Suk;Lee, Hwi-Yong;Song, Beom-Yong
    • Journal of Acupuncture Research
    • /
    • v.25 no.6
    • /
    • pp.67-76
    • /
    • 2008
  • Objectives : The 7-zone-diagnostic system is a diagnostic device to predetermine bodily locations by measuring the energy of body. This study was to investigate the relation between the different patterns of Zone 1, 2, 3 of Factor AA in CP-6000A(VEGA, Germany), 7-zone-diagnostic system and clinical parameters. The purpose of this study was relation Korean traditional medicine and western medicine with the data from 7-zone-diagnostic system and the clinical parameters. Methods : This study was carried out with the data from some clinical parameters. We made three groups according to the Factor AA patterns of CP-6000A. The Factor AA pattern of Group A is that the red bar graph of zone 1, 2, 3 were higher than the normal range and the others were the normal range. The Factor AA pattern of Group B was that the red bar graph of zone 1, 2, 3 was the normal range and the others were the normal range. The Factor AA pattern of Group C was that the red bar graph of zone 1, 2, 3 was lower than the normal range and the others were the normal range. After the data from clinical parameters to correspond with conditions of each group were selected, the data from clinical parameters among each groups analyzed statistically. Results : The values of GOT, GPT, r-GPT, Triglyceride, BUN, Uric acid of group A was higher than group C. Gastroscope of group A and B was higher than group C. Conclusions : It is thought that the red bar graph of zone 1, 2, 3 is higher, the group has the higher energy and the energy has a character of fire(熱). Those patterns have a high risk of hyperlipermia and liver, stomach disease.

  • PDF

Effect of Food Preferance on the Health Status of Adults in Iksan City (식품 기호가 성인의 건강상태에 미치는 영향 -익산시를 중심으로-)

  • Shin, Mee-Kung;Han, Sung-Hee
    • Journal of the East Asian Society of Dietary Life
    • /
    • v.7 no.2
    • /
    • pp.181-198
    • /
    • 1997
  • The purpose of this study was to investigated relationship between heath status and food preference of male and fermale adults who live in Iksan City, Cheonbuk, Korea. The subjects consisted of 96 male and 93 fermale adults were aged 20 to 70 years old. Each subject was interviewed to get information of food preference. Blood samples were taken concentration of serum in hemoglobin, glucose, total cholesterol, GOT(glutamic oxaloacetic transaminase), GPT(glutamic pyruvic transaminase) were measured. The results obtained were as follows: Among the food preference were like, dislike and ordinary answered to male and fermale adults the normal average of serum concentration with hemoglobin level showed 15.4, 14.2, 15.5, 12.9, 15.8 and 13.2g/dl, glucose level showed 85.8, 86.1, 87.5, 88.1, 87.9 and 86.1mg/dl, total cholesterol level showed 183.1, 185.0, 172.4, 193.5, 181.2 and 184.0mg/dl, GOT level showed 4.8, 23.4, 24.8, 23.9, 24.9 and 21.7ppm, GPT level showed 22.7, 20.2, 26.3, 18.5, 22.5 and 18.4ppm respectively. The abnormal average of serum concentration with hemoglobin level showed 11.1, 10.8, 12.2, 11.3, 12.5 and 11.0g/dl, abnormal glucose level showed 155.7 168.5, 166.2, 134.1, 124.1, 130.1, abnormal total cholesterol level showed 260.3, 273.7, 255.2, 286.5, 255.9 and 251.8mg/dl, abnormal GOT level showed 58.8, 66.8, 51.8, 50.3, 51.2 and 51.0ppm abnormal GPT level showed 54.3, 48.6, 51.3, 50.2, 53.2 and 45.5ppm respectively.

  • PDF

Case of Oriental Obesity Treatment's Effect on Improvement of Nonalcoholic Steatohepatitis Patient's Liver Function (한방비만치료를 통한 비알코올성 지방간염 의증 환자의 간기능 개선 1례 보고)

  • Choi, Bin-Hye;Kim, Dong-Woo;Park, Kyung;Kim, Dae-Jun;Byun, Joon-Seok;Hur, Jin-Il
    • Journal of Physiology & Pathology in Korean Medicine
    • /
    • v.20 no.6
    • /
    • pp.1785-1788
    • /
    • 2006
  • Nonalcoholic steatohepatitis(NASH) may progress to advanced liver disease. The diagnosis is made on liver biopsy when investigating a patient with raised transaminases and an otherwise negative biochemical and serological work-up. The subject was a obese male patient who had unexplained raised GOT, GPT. He had no alcoholic consumption and drug ingested. On serological examination, HBsAg and Anti-HCV test are negative. The subject was diagnosed as NASH, and was treated with oriental treatment for obesity. After 2months treatment the raised GOT, GPT decreased to normal range.

Development of Block-based Code Generation and Recommendation Model Using Natural Language Processing Model (자연어 처리 모델을 활용한 블록 코드 생성 및 추천 모델 개발)

  • Jeon, In-seong;Song, Ki-Sang
    • Journal of The Korean Association of Information Education
    • /
    • v.26 no.3
    • /
    • pp.197-207
    • /
    • 2022
  • In this paper, we develop a machine learning based block code generation and recommendation model for the purpose of reducing cognitive load of learners during coding education that learns the learner's block that has been made in the block programming environment using natural processing model and fine-tuning and then generates and recommends the selectable blocks for the next step. To develop the model, the training dataset was produced by pre-processing 50 block codes that were on the popular block programming language web site 'Entry'. Also, after dividing the pre-processed blocks into training dataset, verification dataset and test dataset, we developed a model that generates block codes based on LSTM, Seq2Seq, and GPT-2 model. In the results of the performance evaluation of the developed model, GPT-2 showed a higher performance than the LSTM and Seq2Seq model in the BLEU and ROUGE scores which measure sentence similarity. The data results generated through the GPT-2 model, show that the performance was relatively similar in the BLEU and ROUGE scores except for the case where the number of blocks was 1 or 17.

Safety Verification Techniques of Privacy Policy Using GPT (GPT를 활용한 개인정보 처리방침 안전성 검증 기법)

  • Hye-Yeon Shim;MinSeo Kweun;DaYoung Yoon;JiYoung Seo;Il-Gu Lee
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.34 no.2
    • /
    • pp.207-216
    • /
    • 2024
  • As big data was built due to the 4th Industrial Revolution, personalized services increased rapidly. As a result, the amount of personal information collected from online services has increased, and concerns about users' personal information leakage and privacy infringement have increased. Online service providers provide privacy policies to address concerns about privacy infringement of users, but privacy policies are often misused due to the long and complex problem that it is difficult for users to directly identify risk items. Therefore, there is a need for a method that can automatically check whether the privacy policy is safe. However, the safety verification technique of the conventional blacklist and machine learning-based privacy policy has a problem that is difficult to expand or has low accessibility. In this paper, to solve the problem, we propose a safety verification technique for the privacy policy using the GPT-3.5 API, which is a generative artificial intelligence. Classification work can be performed evenin a new environment, and it shows the possibility that the general public without expertise can easily inspect the privacy policy. In the experiment, how accurately the blacklist-based privacy policy and the GPT-based privacy policy classify safe and unsafe sentences and the time spent on classification was measured. According to the experimental results, the proposed technique showed 10.34% higher accuracy on average than the conventional blacklist-based sentence safety verification technique.

A Comparative Study on Discrimination Issues in Large Language Models (거대언어모델의 차별문제 비교 연구)

  • Wei Li;Kyunghwa Hwang;Jiae Choi;Ohbyung Kwon
    • Journal of Intelligence and Information Systems
    • /
    • v.29 no.3
    • /
    • pp.125-144
    • /
    • 2023
  • Recently, the use of Large Language Models (LLMs) such as ChatGPT has been increasing in various fields such as interactive commerce and mobile financial services. However, LMMs, which are mainly created by learning existing documents, can also learn various human biases inherent in documents. Nevertheless, there have been few comparative studies on the aspects of bias and discrimination in LLMs. The purpose of this study is to examine the existence and extent of nine types of discrimination (Age, Disability status, Gender identity, Nationality, Physical appearance, Race ethnicity, Religion, Socio-economic status, Sexual orientation) in LLMs and suggest ways to improve them. For this purpose, we utilized BBQ (Bias Benchmark for QA), a tool for identifying discrimination, to compare three large-scale language models including ChatGPT, GPT-3, and Bing Chat. As a result of the evaluation, a large number of discriminatory responses were observed in the mega-language models, and the patterns differed depending on the mega-language model. In particular, problems were exposed in elder discrimination and disability discrimination, which are not traditional AI ethics issues such as sexism, racism, and economic inequality, and a new perspective on AI ethics was found. Based on the results of the comparison, this paper describes how to improve and develop large-scale language models in the future.

Screening of Medicinal Plants Having Hepatoprotective Activity Effects with Primary Cultured Hepatocytes Intoxicated Using Carbon tetrachloride Cytotoxicity ($CCl_4$로 독성유발시킨 초대배양 간세포를 이용하여 간세포 보호효과를 나타내는 생약류의 검색)

  • Lee, June-Woo;Choi, Joon-Han;Kang, Sang-Mo
    • Korean Journal of Pharmacognosy
    • /
    • v.23 no.4
    • /
    • pp.268-275
    • /
    • 1992
  • We studied to screen medicinal plants having hepatoprotective activity with the primary cultured rat hepatocytes intoxicated with carbon tetrachloride cytotoxicity. The lowest concentration and treatment time of carbon tetrachloride giving the greatest intoxication to the primary cultured hepatocytes were observed in 10mM and 60 minutes, respectively. GTP and GOT activity of culture broth of the primary cultured rat hepatocytes intoxicated by $CCl_4$ cytotoxicity at this condition were increased 135.9% and 178.3% compared with that of the primaries cultured hepatocytes not treated with $CCl_4$, respectively. This increased GPT activity was inhibited by glycyrrizin, which was known to have hepatoprotective activity, and the inhibition activity was dependent on the concentration of glycyrrhizin. Forty species among the extracts obtained from 117 species of medicinal plants were shown to have the hepatoprotective activity. Among these 40 species, Prunus persica, Scutellaria baicalensis, Astragalus membranaceus, Tribulus terrestris, Caragana chamlagu, Acanthopanax sessiliflorum and Achyranthes japonica were indicated a lower GPT activity than that of Glycyrrhiza uralensis containing glycyrrhizin and GPT activity of these were indicated 75.5%, 70.0%, 59.0%, 77.5%, 60.0%, 75.0% and 79.0%, respectively.

  • PDF