Financial assets have the basic characteristics of risk, profitability, liquidity and so on. How to effectively complete the dynamic monitoring of comprehensive risk and investment performance of financial assets is still an important content of asset investment and management business. This paper takes the characteristic engineering as the basic knowledge theory, takes five stocks in China's A-share market as the research object, uses mathematical statistics and other methods to calculate the economic characteristics and physical characteristics of the selected stocks, and constructs the Comprehensive risk index and Investment performance index through the CRITIC-FAHP subjective-objective weighting method, so as to complete the comprehensive calculation and dynamic evaluation of the risk value and investment performance of the selected financial assets. The calculation results show that the comprehensive index constructed in this paper has high accuracy and good stability, which can avoid the evaluation deviation of the single factor model to a certain extent, and scientifically, comprehensively and deeply reflect the complex characteristics and internal laws of financial assets; At the same time, it can also be combined with Markowitz's Mean-Variance model to optimize its parameter structure and configuration, so as to provide some reference for investors or salespeople to make investment decisions.
{"title":"Research on the Dynamic Assessment of Comprehensive Risk Measurement and Investment Performance of Financial Assets","authors":"Yeyong Zhang, Yusen Liu, Sama Zhu","doi":"10.1145/3584816.3584821","DOIUrl":"https://doi.org/10.1145/3584816.3584821","url":null,"abstract":"Financial assets have the basic characteristics of risk, profitability, liquidity and so on. How to effectively complete the dynamic monitoring of comprehensive risk and investment performance of financial assets is still an important content of asset investment and management business. This paper takes the characteristic engineering as the basic knowledge theory, takes five stocks in China's A-share market as the research object, uses mathematical statistics and other methods to calculate the economic characteristics and physical characteristics of the selected stocks, and constructs the Comprehensive risk index and Investment performance index through the CRITIC-FAHP subjective-objective weighting method, so as to complete the comprehensive calculation and dynamic evaluation of the risk value and investment performance of the selected financial assets. The calculation results show that the comprehensive index constructed in this paper has high accuracy and good stability, which can avoid the evaluation deviation of the single factor model to a certain extent, and scientifically, comprehensively and deeply reflect the complex characteristics and internal laws of financial assets; At the same time, it can also be combined with Markowitz's Mean-Variance model to optimize its parameter structure and configuration, so as to provide some reference for investors or salespeople to make investment decisions.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"304 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123334584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To support the institution's efficient operation, accounting information systems are crucial, thus it is also required to have an accounting information system that is backed by computerized information technology. This study will ascertain if user participation, individual technical proficiency, training and education programs, top management support, and formalization of system development have an impact on the functionality of the banking accounting information system. 104 people made up the sample for this study, which was gathered using a purposive sampling approach. Multiple linear regression analysis is the method utilized for analysis. The findings demonstrated that top management support, formalization of system development, user participation, personal technical abilities, training and education programs, and technical proficiency all improved the performance of accounting information systems.
{"title":"Analysis of Factors Affecting Accounting Information System Performance on Banking Company","authors":"B. Handoko, G. Thomas, Lely Indriati","doi":"10.1145/3584816.3584825","DOIUrl":"https://doi.org/10.1145/3584816.3584825","url":null,"abstract":"To support the institution's efficient operation, accounting information systems are crucial, thus it is also required to have an accounting information system that is backed by computerized information technology. This study will ascertain if user participation, individual technical proficiency, training and education programs, top management support, and formalization of system development have an impact on the functionality of the banking accounting information system. 104 people made up the sample for this study, which was gathered using a purposive sampling approach. Multiple linear regression analysis is the method utilized for analysis. The findings demonstrated that top management support, formalization of system development, user participation, personal technical abilities, training and education programs, and technical proficiency all improved the performance of accounting information systems.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123553377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The crude oil prices, which were stable for consecutive years, have been on a roller coaster since COVID-19. Owing to supply chain crises caused by the pandemic, the war between Russia and Ukraine, and the mismatch between excessive monetary policies and environmental protection policies, oil prices fell into negative territory in early 2020 unprecedentedly and hit new highs in recent days. On account of its universal approximation ability for any nonlinear function, the neural network has received substantial attention in asset price prediction. As a data-driven model, there is no doubt that the neural network can digest the past to predict the future. However, it cannot effectively predict those distinctive patterns that did not appear before, which is the case right now. In order to address this problem, a grey box adaptive Recurrent Neural Network (RNN) model based on feedback control in the control engineering field is proposed in this paper to compensate for the prediction error of the neural network. According to the experimental data, the correlation coefficients of the Adaptive Long Short-Term Memory (ALSTM) and Adaptive Gate Recurrent Unit (AGRU) proposed in this paper are 0.9895 and 0.9886, respectively, and the Root Mean Square Errors (RMSE) of these two models are 3.2184 and 3.3546, respectively. Therefore, the proposed models can improve prediction accuracy.
{"title":"GRU and LSTM Based Adaptive Prediction Model of Crude Oil Prices: Post-Covid-19 and Russian Ukraine War","authors":"Yingpeng Cai, Ning Zhang, Shimu Zhang","doi":"10.1145/3584816.3584818","DOIUrl":"https://doi.org/10.1145/3584816.3584818","url":null,"abstract":"The crude oil prices, which were stable for consecutive years, have been on a roller coaster since COVID-19. Owing to supply chain crises caused by the pandemic, the war between Russia and Ukraine, and the mismatch between excessive monetary policies and environmental protection policies, oil prices fell into negative territory in early 2020 unprecedentedly and hit new highs in recent days. On account of its universal approximation ability for any nonlinear function, the neural network has received substantial attention in asset price prediction. As a data-driven model, there is no doubt that the neural network can digest the past to predict the future. However, it cannot effectively predict those distinctive patterns that did not appear before, which is the case right now. In order to address this problem, a grey box adaptive Recurrent Neural Network (RNN) model based on feedback control in the control engineering field is proposed in this paper to compensate for the prediction error of the neural network. According to the experimental data, the correlation coefficients of the Adaptive Long Short-Term Memory (ALSTM) and Adaptive Gate Recurrent Unit (AGRU) proposed in this paper are 0.9895 and 0.9886, respectively, and the Root Mean Square Errors (RMSE) of these two models are 3.2184 and 3.3546, respectively. Therefore, the proposed models can improve prediction accuracy.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127037824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
P. Brandtner, Stefan Schober, Robert Zimmermann, F. Staberhofer
The complexity and uncertainty in Supply Chain Management (SCM) has grown radically over the last years. New technologies provide an avenue for improving SCM activities. In particular, the Internet-of-Things (IoT) is one of the technological advances that has received quite some attention in SCM literature. However, especially for smaller countries such as Austria, the actual status of IoT application in SCM is low and research is often limited to analyzing theoretical potentials. The current paper elaborates the status-quo of IoT in eight different industries in Austria by means of expert interviews. Results show, that IoT is only applied in a very limited way. Still, practitioners agree that it offers huge potential, e.g., to increase supply chain transparency, improve planning in SCM or provide real-time information as basis for risk handling. The main benefits of IoT are seen in form of improved process quality, higher level of customer satisfaction due to tracking and tracing, provision of additional real time data, and the creation of digital supply chain twins. Each analyzed company plans to implement IoT in SCM in the future. The paper provides several starting points for practitioners aiming to implement IoT in SCM. Our results also provide several opportunities for future research, e.g., to compare our findings for Austria with findings from other countries with especial focus on SMEs.
{"title":"Status-Quo of IoT in Supply Chain Management - Applications, Potentials and Challenges in Austria: Status-Quo of IoT in Supply Chain Management","authors":"P. Brandtner, Stefan Schober, Robert Zimmermann, F. Staberhofer","doi":"10.1145/3584816.3584837","DOIUrl":"https://doi.org/10.1145/3584816.3584837","url":null,"abstract":"The complexity and uncertainty in Supply Chain Management (SCM) has grown radically over the last years. New technologies provide an avenue for improving SCM activities. In particular, the Internet-of-Things (IoT) is one of the technological advances that has received quite some attention in SCM literature. However, especially for smaller countries such as Austria, the actual status of IoT application in SCM is low and research is often limited to analyzing theoretical potentials. The current paper elaborates the status-quo of IoT in eight different industries in Austria by means of expert interviews. Results show, that IoT is only applied in a very limited way. Still, practitioners agree that it offers huge potential, e.g., to increase supply chain transparency, improve planning in SCM or provide real-time information as basis for risk handling. The main benefits of IoT are seen in form of improved process quality, higher level of customer satisfaction due to tracking and tracing, provision of additional real time data, and the creation of digital supply chain twins. Each analyzed company plans to implement IoT in SCM in the future. The paper provides several starting points for practitioners aiming to implement IoT in SCM. Our results also provide several opportunities for future research, e.g., to compare our findings for Austria with findings from other countries with especial focus on SMEs.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121502129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study investigates the importance of the social media on Chinese students’ choice of private universities in China and develops strategies to use different type of word-of-mouth. This study adopts a qualitative approach with a plan to conduct an in-depth interview with 25 Chinese private university students in mainland China. This research is also anticipated to add to the roles of offline word-of-mouth, the source credibility, and their relationships. The results indicate the following: 1) Chinese social media online word-of-mouth will directly influence Chinese students’ intention to select private universities. 2) Offline word-of-mouth will indirectly influence Chinese students’ intention to select private universities 3) Information source credibility plays a mediation role between offline word-of-mouth and intention to select private universities. The findings of this study will provide applied knowledge and managerial recommendations for private university who target Chinese students, need to be more actively involved in social media marketing by including online and offline word-of-mouth interactively.
{"title":"The Influence of Social Media on Chinese Students' Choice of Private Universities in China","authors":"Xiaolie Qi","doi":"10.1145/3584816.3584841","DOIUrl":"https://doi.org/10.1145/3584816.3584841","url":null,"abstract":"This study investigates the importance of the social media on Chinese students’ choice of private universities in China and develops strategies to use different type of word-of-mouth. This study adopts a qualitative approach with a plan to conduct an in-depth interview with 25 Chinese private university students in mainland China. This research is also anticipated to add to the roles of offline word-of-mouth, the source credibility, and their relationships. The results indicate the following: 1) Chinese social media online word-of-mouth will directly influence Chinese students’ intention to select private universities. 2) Offline word-of-mouth will indirectly influence Chinese students’ intention to select private universities 3) Information source credibility plays a mediation role between offline word-of-mouth and intention to select private universities. The findings of this study will provide applied knowledge and managerial recommendations for private university who target Chinese students, need to be more actively involved in social media marketing by including online and offline word-of-mouth interactively.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131964526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Previous research has primarily focused on the structure of marriage value and special groups' marriage value and its changing trends, but few have examined public intergenerational tendency to marry. This study constructs a model of moderated chain mediating effects based on social role theory and media communication theory. It explores the chain mediating role of gender roles and gender stereotypes in intimate relationships and the moderating role of negative media information exposure in the effect of birth year on tendency to marry. The results of the study show that:(a) the tendency to marry varies significantly between generations and shows a downward trend; (b)gender roles and gender stereotypes in intimate relationships play a chain mediating role between birth year and tendency to marry;(c) Negative media information exposure positively moderates the relationship between birth year and tendency to marry. Specifically, the greater the exposure to negative media messages, the stronger the negative relationship between birth year and tendency to marry; (d) Negative media information exposure does not moderate the relationship between birth year and gender roles in intimate relationships, nor does it moderate the chain mediating effect between birth years and the tendency to marry through gender roles and gender stereotypes in intimate relationships.
{"title":"The Influence of Birth Years on Tendency to Marry: The Moderating Role of Negative Media Information Exposure","authors":"Yun Gao, Jie Zhou, Zhefei Mao","doi":"10.1145/3584816.3584840","DOIUrl":"https://doi.org/10.1145/3584816.3584840","url":null,"abstract":"Previous research has primarily focused on the structure of marriage value and special groups' marriage value and its changing trends, but few have examined public intergenerational tendency to marry. This study constructs a model of moderated chain mediating effects based on social role theory and media communication theory. It explores the chain mediating role of gender roles and gender stereotypes in intimate relationships and the moderating role of negative media information exposure in the effect of birth year on tendency to marry. The results of the study show that:(a) the tendency to marry varies significantly between generations and shows a downward trend; (b)gender roles and gender stereotypes in intimate relationships play a chain mediating role between birth year and tendency to marry;(c) Negative media information exposure positively moderates the relationship between birth year and tendency to marry. Specifically, the greater the exposure to negative media messages, the stronger the negative relationship between birth year and tendency to marry; (d) Negative media information exposure does not moderate the relationship between birth year and gender roles in intimate relationships, nor does it moderate the chain mediating effect between birth years and the tendency to marry through gender roles and gender stereotypes in intimate relationships.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125025747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Apart from quick monitoring of abnormal changes in a multivariate process, it is also critical to accurately identify the cause of abnormal changes after a signal in multivariate statistical process control. Most diagnosis methods focus on the distribution of mass characteristics such as mean and/or variance. But the quality of a process may be better characterized by the relationship between the response variable and one or more explanatory variables in many applications, which is called profile problems in literatures. This paper develops a Bayesian approach to diagnosis parameter shifts in profile process. The proposed approach not only accurately identifies shift parameters but also provides the probabilities of shift parameters. Compared with existing methods, the proposed approach outperforms them.
{"title":"A Bayesian Approach to Diagnosing General Linear Profiles","authors":"Feng Xu","doi":"10.1145/3584816.3584833","DOIUrl":"https://doi.org/10.1145/3584816.3584833","url":null,"abstract":"Apart from quick monitoring of abnormal changes in a multivariate process, it is also critical to accurately identify the cause of abnormal changes after a signal in multivariate statistical process control. Most diagnosis methods focus on the distribution of mass characteristics such as mean and/or variance. But the quality of a process may be better characterized by the relationship between the response variable and one or more explanatory variables in many applications, which is called profile problems in literatures. This paper develops a Bayesian approach to diagnosis parameter shifts in profile process. The proposed approach not only accurately identifies shift parameters but also provides the probabilities of shift parameters. Compared with existing methods, the proposed approach outperforms them.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121539288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Although cryptocurrencies are catching the fancy of investors for various benefits such as decentralization, low transaction costs, and inflation hedging, their extreme volatility is sometimes keeping many away. Consequently, modeling and forecasting cryptocurrency market volatility are essential to investors’ investment decisions and risk management. However, most previous studies have been limited to Bitcoin volatility, disregarding cryptocurrency market performance as a whole. This study estimates realized volatility of cryptocurrency market with a variety of algorithms employing a portfolio-style technique. After comparison, LSTM networks surpass the conventional GARCH-type models; meanwhile, the hybrid GARCH neural network models perform the worst. This study provides an impetus for a significant number of academics interested in the extreme volatility of cryptocurrencies. Additionally, it illustrates that more sophisticated models may not always lead to better predictive performance.
{"title":"Cryptocurrency Market Volatility Forecasting","authors":"Yiming Wang","doi":"10.1145/3584816.3584823","DOIUrl":"https://doi.org/10.1145/3584816.3584823","url":null,"abstract":"Although cryptocurrencies are catching the fancy of investors for various benefits such as decentralization, low transaction costs, and inflation hedging, their extreme volatility is sometimes keeping many away. Consequently, modeling and forecasting cryptocurrency market volatility are essential to investors’ investment decisions and risk management. However, most previous studies have been limited to Bitcoin volatility, disregarding cryptocurrency market performance as a whole. This study estimates realized volatility of cryptocurrency market with a variety of algorithms employing a portfolio-style technique. After comparison, LSTM networks surpass the conventional GARCH-type models; meanwhile, the hybrid GARCH neural network models perform the worst. This study provides an impetus for a significant number of academics interested in the extreme volatility of cryptocurrencies. Additionally, it illustrates that more sophisticated models may not always lead to better predictive performance.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122820588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Roland Ross F. Flame, Y. Prasetyo, Reny Nadlifatin, Irene Dyah Ayuwati, S. F. Persada, Thanatorn Chuenyindee
Due to pandemic Covid-19, there is an increase and rough transition into remote work. Communication tools/platforms are softwares used by industries to facilitate different functionalities like remote technical support and communication. Especially for service industries, coordinators and engineers adapted on using these tools to support internal and external communications. For a certain machine service company, Skype and Microsoft Teams are the main communication tools used. The objective of this study is to determine the usability/user experience of these tools of engineers and coordinators on their daily activities. System Usability Scale were used to evaluate their user experience. As interpreted using the Curved Grading Scale, only the use of Microsoft Teams of Coordinators is graded as D, and the rest are graded as F. Based on the results on the user experience of coordinators and engineers using platforms Microsoft Teams and Skype, the low scores show that they are struggling with the usability of these tools due to drastic change and adaptability and limitation of activities that these tools can only perform.
由于2019冠状病毒病(Covid-19)大流行，远程工作有所增加，过渡也很艰难。通信工具/平台是行业使用的软件，用于促进远程技术支持和通信等不同功能。特别是对于服务行业，协调员和工程师适应使用这些工具来支持内部和外部通信。对于某机器服务公司来说，Skype和Microsoft Teams是主要使用的通信工具。本研究的目的是确定工程师和协调员在日常活动中使用这些工具的可用性/用户体验。使用系统可用性量表来评估他们的用户体验。根据曲线评分量表的解释，只有Microsoft Teams of coordinator的使用被评为D，其余的都被评为f。根据协调员和工程师使用Microsoft Teams和Skype平台的用户体验结果，低分数表明他们正在努力解决这些工具的可用性，因为这些工具的变化很大，而且这些工具只能执行活动的适应性和局限性。
{"title":"Usability Evaluation of Communication Tools Used as Remote Support in Machine Service Industry: A Comparison between Microsoft Teams and Skype","authors":"Roland Ross F. Flame, Y. Prasetyo, Reny Nadlifatin, Irene Dyah Ayuwati, S. F. Persada, Thanatorn Chuenyindee","doi":"10.1145/3584816.3584834","DOIUrl":"https://doi.org/10.1145/3584816.3584834","url":null,"abstract":"Due to pandemic Covid-19, there is an increase and rough transition into remote work. Communication tools/platforms are softwares used by industries to facilitate different functionalities like remote technical support and communication. Especially for service industries, coordinators and engineers adapted on using these tools to support internal and external communications. For a certain machine service company, Skype and Microsoft Teams are the main communication tools used. The objective of this study is to determine the usability/user experience of these tools of engineers and coordinators on their daily activities. System Usability Scale were used to evaluate their user experience. As interpreted using the Curved Grading Scale, only the use of Microsoft Teams of Coordinators is graded as D, and the rest are graded as F. Based on the results on the user experience of coordinators and engineers using platforms Microsoft Teams and Skype, the low scores show that they are struggling with the usability of these tools due to drastic change and adaptability and limitation of activities that these tools can only perform.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116753011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaogang Zhao, Ge Li, Hai Shen, Yiwei Dang, Jun Hou, Siwei Dong
To solve the problem of coarse-grained results in the research of topic content prediction, this paper proposes a prediction method for the topic content from the perspective of bi-directional sentiment classification. Firstly, the method uses SnowNLP to classify the sentiment of online reviews; secondly, LDA model is applied to extract the topics and entropy is used to sort topics; finally, Word2Vec is applied to achieve the prediction of the topic content. Example calculation shows that this method effectively solves the problem of coarse-grained prediction results of online reviews’ topic content, and presents the prediction results from positive and negative sentiments. The average precision of positive topics is 86.67%, and the average precision of negative topics is 80.00%.
{"title":"Research on the Topic Content Prediction of Online Reviews: from the Perspective of Bi-directional Sentiment Classification","authors":"Xiaogang Zhao, Ge Li, Hai Shen, Yiwei Dang, Jun Hou, Siwei Dong","doi":"10.1145/3584816.3584842","DOIUrl":"https://doi.org/10.1145/3584816.3584842","url":null,"abstract":"To solve the problem of coarse-grained results in the research of topic content prediction, this paper proposes a prediction method for the topic content from the perspective of bi-directional sentiment classification. Firstly, the method uses SnowNLP to classify the sentiment of online reviews; secondly, LDA model is applied to extract the topics and entropy is used to sort topics; finally, Word2Vec is applied to achieve the prediction of the topic content. Example calculation shows that this method effectively solves the problem of coarse-grained prediction results of online reviews’ topic content, and presents the prediction results from positive and negative sentiments. The average precision of positive topics is 86.67%, and the average precision of negative topics is 80.00%.","PeriodicalId":113982,"journal":{"name":"Proceedings of the 2023 6th International Conference on Computers in Management and Business","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131488438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：