With Chinese science fiction films and TV series gradually entering the international stage,this study focuses on English-language reviews on Internet Movie Database(IMDb)and Letterboxd.Using Latent Dirichlet Allocati...With Chinese science fiction films and TV series gradually entering the international stage,this study focuses on English-language reviews on Internet Movie Database(IMDb)and Letterboxd.Using Latent Dirichlet Allocation(LDA)topic modeling,it analyzes the international reception of the Chinese sci-fi work The Three-Body Problem,aiming to uncover the main discussion points and differences in attention among foreign audiences for the two versions of The Three-Body Problem through text-mining techniques.The findings reveal differences between the two versions in terms of target audience,cultural presentation,adaptation evaluation,and focus in plot discussion.Moreover,this study explores new pathways for Chinese sci-fi media to go global from four dimensions:channel,content,communicator,and recipient.The study provides not only a novel perspective for understanding the international influence of Chinese sci-fi media but also empirical support for strategies in the international dissemination of Chinese cultural products.展开更多
China’s environmental governance strategy provides a distinctive pathway for integrating sustainable development into national policy.Understanding its policy trajectory is essential for assessing China’s contributi...China’s environmental governance strategy provides a distinctive pathway for integrating sustainable development into national policy.Understanding its policy trajectory is essential for assessing China’s contribution to global sustainable development and the United Nations Sustainable Development Goals(SDGs).This study constructs a comprehensive database of 425 national environmental governance policy documents issued between 1978 and 2022 and applies Latent Dirichlet Allocation(LDA)modeling to examine the evolution of policy themes and discourse.The results show that China’s environmental governance has undergone four stages-initial exploration,detailed development,transformative leap,and diverse prosperity-reflecting a progressive shift toward more integrated and coordinated governance.Policy priorities have evolved from a primary focus on pollution control and energy transition to an emphasis on institutional construction and organizational reform,thereby strengthening alignment with the SDGs.This transformation is characterized by recurring developmental themes and increasingly preventive,forward-looking,and system-oriented governance approaches.Moreover,the co-evolution of policy concepts and implementation has driven a transition from localized,end-of-pipe responses to comprehensive governance frameworks,alongside a shift from normative guidance towards effectiveness-oriented policy design.By employing a data-driven text analysis approach,this study offers a systematic framework for tracing long-term policy evolution and assessing its implications for sustainable development.展开更多
This study investigates how universities are developing normativeframeworks to regulate the use of generative AI tools in higher education, with aparticular focus on balancing empowerment and discipline. Drawing on th...This study investigates how universities are developing normativeframeworks to regulate the use of generative AI tools in higher education, with aparticular focus on balancing empowerment and discipline. Drawing on theoreticallenses such as Foucault’s discipline theory and contemporary AI ethics, the paperanalyzes policy documents from institutions including Harvard, Oxford, and severaltop Chinese universities. Using Latent Dirichlet Allocation (LDA) topic modeling,the study reveals five dominant governance themes—ranging from academicintegrity enforcement to pedagogical empowerment. The findings highlight a globalshift from restrictive to balanced, ethics-informed AI governance, with significantdisciplinary variations. The paper concludes by proposing a “principledpermissiveness” model that combines transparency, accountability, andpedagogical innovation in future AI governance.展开更多
The progress of IT technology such as social network and mobile payment and the change of social economic environment promote the emergence of sharing economy.As a subversive business model,the sharing economy is grow...The progress of IT technology such as social network and mobile payment and the change of social economic environment promote the emergence of sharing economy.As a subversive business model,the sharing economy is growing at an alarming rate all over the world.However,the influencing factors of consumers'continuous participation in the sharing economy are not clear.The paper aims to clarify the relationship between consumer perceived value and repeat purchase intention in the sharing economy.Taking the sharing economy platform(Airbnb)as an example,it proposes a dimension framework of consumer perceived value in peer-to-peer(P2P)accommodation rental service,including functional value,hedonic value,epistemic value and social relationship value.This paper used big data technology to crawl online reviews of P2P accommodation platform.LDA(Latent Dirichlet Allocation)topic model and sentiment analytics method were applied to construct the measurement indicators of perceived value based on online reviews.And repeat purchase intention variables were extracted from online reviews.Then structural equation model was used to examine the effect of perceived value dimensions on it.The paper identified that perceived value has a positive impact on consumers'repurchase intention in P2P accommodation.Also,social relationship value was considered as the most important influencing factor.展开更多
In the modern economy,startups are not only significant drivers of innovation and technological progress but also key players in addressing employment issues and promoting economic diversification.However,startups oft...In the modern economy,startups are not only significant drivers of innovation and technological progress but also key players in addressing employment issues and promoting economic diversification.However,startups often face substantial operational risks and uncertainties in their early stages,especially regarding financing.To uncover the impact of different resource allocations and strategic choices on financing success,this study proposes a predictive method based on the latent Dirichlet allocation(LDA)topic model and deep neural networks through an in-depth analysis of startup financing cases.We systematically collected description text data from 2,000 startups and extracted text features from these descriptions using the LDA topic model.These features,combined with several traditional numerical indicators such as industry,product type,technology type,number of employees,and company size,were used to train a deep neural network to predict startup financing outcomes.The experimental results show that the prediction performance based on the LDA topic model is significantly better than that of traditional models relying solely on numerical data.This highlights the importance of text features in predicting the success of startup financing.展开更多
Ski tourism has become a hotspot in the tourism industry due to its high revisit rate.Accurate assessment of its experience quality is crucial for enhancing tourists’revisit intentions and promoting the high-quality ...Ski tourism has become a hotspot in the tourism industry due to its high revisit rate.Accurate assessment of its experience quality is crucial for enhancing tourists’revisit intentions and promoting the high-quality development of the ski industry.Based on the expectation-disconfirmation theory,this study comprehensively applies the LDA model,Text-CNN model,and Importance-Performance Analysis(IPA)to examine 103503 online reviews from 55 ski resorts across nearly 10 ski seasons(2015/2016-2024/2025)in China.It constructs evaluation indicators for ski tourism experience quality and conducts an evaluation and comparison of the experience quality in the four major ski tourism areas:Northeast,North,Northwest,and East of China.The results indicate:(1)16 influencing factors on ski tourism experience quality were identified,including the newly recognized factors of Ski Instructor Quality and Peer Interaction;(2)In terms of the evolutionary characteristics of experience quality,Established ski regions(Northeast and Northwest)show slow experience improvements,while emerging regions(North and East China)exhibit rapid progress;(3)Overall,North China leads in experience quality,followed by Northeast,Northwest,and East of China;(4)In comparing influencing factors,Natural Scenery,Emotional Perception,and Peer Interaction are common advantages across the four ski tourism areas,while Price Perception is a shared disadvantage.This study systematically evaluated the spatiotemporal heterogeneity of experience quality in major ski tourism areas of China,providing theoretical basis and practical insights for precise improvement of tourism experiences in various regions.展开更多
Architectural programming is of significant importance in improving urban planning efficiency,enhancing the sustainability of the construction industry,and supporting the development of social infrastructure.However,d...Architectural programming is of significant importance in improving urban planning efficiency,enhancing the sustainability of the construction industry,and supporting the development of social infrastructure.However,due to its broad scope and complex content,research in this area exhibits diverse and scattered characteristics.To comprehensively understand the current status,progress,and future directions of architectural programming research,and to provide recommendations for both China and other countries,this study conducted a comparative review of relevant literature using a mixed method approach of bibliometrics,latent Dirichlet allocation(LDA)topic modeling,and systematic review.The study summarized the differences between China and other countries in six topics within the field of architectural programming:(1)intelligent and digital methods,(2)sustainability and practices,(3)project management and decision support,(4)urban planning and existing development,(5)social infrastructure and public services,and(6)architectural education and talent cultivation.This study provides an overview and comparative analysis on architectural programming,offering important reference for future research and practice,and promoting the overall development of the construction industry.展开更多
Tracking and investigating tourist satisfaction and accurately identifying the key factors that affect tourist satisfaction have always been among the top priorities for academia and tourist attraction operators.With ...Tracking and investigating tourist satisfaction and accurately identifying the key factors that affect tourist satisfaction have always been among the top priorities for academia and tourist attraction operators.With the rise of online travel,analysis based on online comments has become an important method for tracking and surveying tourist satisfaction.This article examined the online comments of tourists for the Panjin Red Beach Scenic Corridor Scenic Area(hereinafter referred to as Red Beach)on Ctrip as an example.Using natural language processing to classify the tourist evaluations into topics,the main topics of concern were identified as tourism services,tourism attractions,scenic area management,and tourism experience.Through the 5-level rating of Ctrip’s online gaming customer satisfaction,an analysis was conducted on tourist satisfaction and the topics of greatest concern to the tourists were ranked.The results showed that the satisfaction levels from high to low are:tourism experience,tourism attractions,scenic area management,and tourism services.Therefore,satisfaction with related content under the service topic was the lowest so this aspect urgently needs to be improved and enhanced.展开更多
The Safety Technical Specification for Electric Bicycles(GB 17761–2018, China) has been in effect for over six years, yet its influence on consumer purchase behaviour remains unclear. This study examines public perce...The Safety Technical Specification for Electric Bicycles(GB 17761–2018, China) has been in effect for over six years, yet its influence on consumer purchase behaviour remains unclear. This study examines public perceptions of the specification and its impact on electric bicycle purchase decisions. Using Latent Dirichlet Allocation(LDA) to analyse 20, 971 social media comments, combined with sentiment analysis, a purchase behaviour model was developed. Additionally, 446 valid survey responses were analysed using Partial Least Squares Structural Equation Modelling to identify key influencing factors and their pathways. Bayesian network analysis was then employed to quantify the effects of these factors on purchase behaviour. The results reveal that attitudes and perceived safety are the most significant determinants of electric bicycle purchases. Furthermore, trust, perceived usefulness and face consciousness have a substantial influence on consumer attitudes. Regarding the specification's impact, the findings suggest that public trust and perception of the regulation positively contribute to purchase behaviour. This research provides a robust framework for understanding the drivers of electric bicycle purchase behaviour, supporting the sustainable and regulated growth of China's electric bicycle industry.展开更多
With the rapid growth of online shopping platforms, more and more customers intend to share theirshopping experience and product reviews on the Internet. Both large quantity and various forms ofonline reviews bring di...With the rapid growth of online shopping platforms, more and more customers intend to share theirshopping experience and product reviews on the Internet. Both large quantity and various forms ofonline reviews bring difficulties for potential consumers to summary all the heterogenous reviews forreference. This paper proposes a new ranking method through online reviews based on differentaspects of the alternative products, which combines both objective and subjective sentiment values.Firstly, weights of these aspects are determined with LDA topic model to calculate the objectivesentiment value of the product. During this process, the realistic meaning of each aspect is alsosummarized. Then, consumers＇ personalized preferences are taken into consideration while calculatingtotal scores of alternative products. Meanwhile, comparative superiority between every two productsalso contributes to their final scores. Therefore, a directed graph model is constructed and the finalscore of each product is computed by improved PageRank algorithm. Finally, a case study is given toillustrate the feasibility and effectiveness of the proposed method. The result demonstrates that whileconsidering only objective sentiment values of the product, the ranking result obtained by our proposedmethod has a strong correlation with the actual sales orders. On the other hand, if consumers expresssubjective preferences towards a certain aspect, the final ranking is also consistent with the actualperformance of alternative products. It provides a new research idea for online customer review miningand personalized recommendation.展开更多
基金the General Project of the National Social Science Fund,"Research on Social Anxiety Relief through New Mainstream Media"(Approval No.:23BXW068).
文摘With Chinese science fiction films and TV series gradually entering the international stage,this study focuses on English-language reviews on Internet Movie Database(IMDb)and Letterboxd.Using Latent Dirichlet Allocation(LDA)topic modeling,it analyzes the international reception of the Chinese sci-fi work The Three-Body Problem,aiming to uncover the main discussion points and differences in attention among foreign audiences for the two versions of The Three-Body Problem through text-mining techniques.The findings reveal differences between the two versions in terms of target audience,cultural presentation,adaptation evaluation,and focus in plot discussion.Moreover,this study explores new pathways for Chinese sci-fi media to go global from four dimensions:channel,content,communicator,and recipient.The study provides not only a novel perspective for understanding the international influence of Chinese sci-fi media but also empirical support for strategies in the international dissemination of Chinese cultural products.
基金supported by the Key Project of Jiangsu Social Science Fund and the Key Project of Jiangsu Research Center for Xi Jinping Thought on Socialism with Chinese Characteristics for a New Era(Grant No.26ZXZA017).
文摘China’s environmental governance strategy provides a distinctive pathway for integrating sustainable development into national policy.Understanding its policy trajectory is essential for assessing China’s contribution to global sustainable development and the United Nations Sustainable Development Goals(SDGs).This study constructs a comprehensive database of 425 national environmental governance policy documents issued between 1978 and 2022 and applies Latent Dirichlet Allocation(LDA)modeling to examine the evolution of policy themes and discourse.The results show that China’s environmental governance has undergone four stages-initial exploration,detailed development,transformative leap,and diverse prosperity-reflecting a progressive shift toward more integrated and coordinated governance.Policy priorities have evolved from a primary focus on pollution control and energy transition to an emphasis on institutional construction and organizational reform,thereby strengthening alignment with the SDGs.This transformation is characterized by recurring developmental themes and increasingly preventive,forward-looking,and system-oriented governance approaches.Moreover,the co-evolution of policy concepts and implementation has driven a transition from localized,end-of-pipe responses to comprehensive governance frameworks,alongside a shift from normative guidance towards effectiveness-oriented policy design.By employing a data-driven text analysis approach,this study offers a systematic framework for tracing long-term policy evolution and assessing its implications for sustainable development.
文摘This study investigates how universities are developing normativeframeworks to regulate the use of generative AI tools in higher education, with aparticular focus on balancing empowerment and discipline. Drawing on theoreticallenses such as Foucault’s discipline theory and contemporary AI ethics, the paperanalyzes policy documents from institutions including Harvard, Oxford, and severaltop Chinese universities. Using Latent Dirichlet Allocation (LDA) topic modeling,the study reveals five dominant governance themes—ranging from academicintegrity enforcement to pedagogical empowerment. The findings highlight a globalshift from restrictive to balanced, ethics-informed AI governance, with significantdisciplinary variations. The paper concludes by proposing a “principledpermissiveness” model that combines transparency, accountability, andpedagogical innovation in future AI governance.
基金Evolution Trend and Coping Strategies of Online Public Opinions on Emergencies Based on Big Data Analysis(Grant No.:18CHLJ22)Social Science Planning Project in Shandong Province+1 种基金“Online Public Opinion Concerning Ethnic Factors Based on Big Data Analysis”(Grant No.:2018-GMB-022)Ethnic Research Project of State Ethnic Affairs Commission in China.
文摘The progress of IT technology such as social network and mobile payment and the change of social economic environment promote the emergence of sharing economy.As a subversive business model,the sharing economy is growing at an alarming rate all over the world.However,the influencing factors of consumers'continuous participation in the sharing economy are not clear.The paper aims to clarify the relationship between consumer perceived value and repeat purchase intention in the sharing economy.Taking the sharing economy platform(Airbnb)as an example,it proposes a dimension framework of consumer perceived value in peer-to-peer(P2P)accommodation rental service,including functional value,hedonic value,epistemic value and social relationship value.This paper used big data technology to crawl online reviews of P2P accommodation platform.LDA(Latent Dirichlet Allocation)topic model and sentiment analytics method were applied to construct the measurement indicators of perceived value based on online reviews.And repeat purchase intention variables were extracted from online reviews.Then structural equation model was used to examine the effect of perceived value dimensions on it.The paper identified that perceived value has a positive impact on consumers'repurchase intention in P2P accommodation.Also,social relationship value was considered as the most important influencing factor.
基金Supported by Suzhou Key Laboratory of Artificial Intelligence and Social Governance Technologies(SZS2023007)Smart Social Governance Technology and Innovative Application Platform(YZCXPT2023101)the Innovation System of the Integration between Industry and Education for Smart Governance(CJRH2024101)。
文摘In the modern economy,startups are not only significant drivers of innovation and technological progress but also key players in addressing employment issues and promoting economic diversification.However,startups often face substantial operational risks and uncertainties in their early stages,especially regarding financing.To uncover the impact of different resource allocations and strategic choices on financing success,this study proposes a predictive method based on the latent Dirichlet allocation(LDA)topic model and deep neural networks through an in-depth analysis of startup financing cases.We systematically collected description text data from 2,000 startups and extracted text features from these descriptions using the LDA topic model.These features,combined with several traditional numerical indicators such as industry,product type,technology type,number of employees,and company size,were used to train a deep neural network to predict startup financing outcomes.The experimental results show that the prediction performance based on the LDA topic model is significantly better than that of traditional models relying solely on numerical data.This highlights the importance of text features in predicting the success of startup financing.
基金The R&D Program of Beijing Municipal Education Commission(SM202411626002)。
文摘Ski tourism has become a hotspot in the tourism industry due to its high revisit rate.Accurate assessment of its experience quality is crucial for enhancing tourists’revisit intentions and promoting the high-quality development of the ski industry.Based on the expectation-disconfirmation theory,this study comprehensively applies the LDA model,Text-CNN model,and Importance-Performance Analysis(IPA)to examine 103503 online reviews from 55 ski resorts across nearly 10 ski seasons(2015/2016-2024/2025)in China.It constructs evaluation indicators for ski tourism experience quality and conducts an evaluation and comparison of the experience quality in the four major ski tourism areas:Northeast,North,Northwest,and East of China.The results indicate:(1)16 influencing factors on ski tourism experience quality were identified,including the newly recognized factors of Ski Instructor Quality and Peer Interaction;(2)In terms of the evolutionary characteristics of experience quality,Established ski regions(Northeast and Northwest)show slow experience improvements,while emerging regions(North and East China)exhibit rapid progress;(3)Overall,North China leads in experience quality,followed by Northeast,Northwest,and East of China;(4)In comparing influencing factors,Natural Scenery,Emotional Perception,and Peer Interaction are common advantages across the four ski tourism areas,while Price Perception is a shared disadvantage.This study systematically evaluated the spatiotemporal heterogeneity of experience quality in major ski tourism areas of China,providing theoretical basis and practical insights for precise improvement of tourism experiences in various regions.
基金funded by the National Natural Science Foundation of China(Grant No.52378034)。
文摘Architectural programming is of significant importance in improving urban planning efficiency,enhancing the sustainability of the construction industry,and supporting the development of social infrastructure.However,due to its broad scope and complex content,research in this area exhibits diverse and scattered characteristics.To comprehensively understand the current status,progress,and future directions of architectural programming research,and to provide recommendations for both China and other countries,this study conducted a comparative review of relevant literature using a mixed method approach of bibliometrics,latent Dirichlet allocation(LDA)topic modeling,and systematic review.The study summarized the differences between China and other countries in six topics within the field of architectural programming:(1)intelligent and digital methods,(2)sustainability and practices,(3)project management and decision support,(4)urban planning and existing development,(5)social infrastructure and public services,and(6)architectural education and talent cultivation.This study provides an overview and comparative analysis on architectural programming,offering important reference for future research and practice,and promoting the overall development of the construction industry.
基金The Basic Research Project of Liaoning Provincial Department of Education(LJKMZ20221469)The Economic and Social Development Research Project of Liaoning Province(2024Lsbkt-104)。
文摘Tracking and investigating tourist satisfaction and accurately identifying the key factors that affect tourist satisfaction have always been among the top priorities for academia and tourist attraction operators.With the rise of online travel,analysis based on online comments has become an important method for tracking and surveying tourist satisfaction.This article examined the online comments of tourists for the Panjin Red Beach Scenic Corridor Scenic Area(hereinafter referred to as Red Beach)on Ctrip as an example.Using natural language processing to classify the tourist evaluations into topics,the main topics of concern were identified as tourism services,tourism attractions,scenic area management,and tourism experience.Through the 5-level rating of Ctrip’s online gaming customer satisfaction,an analysis was conducted on tourist satisfaction and the topics of greatest concern to the tourists were ranked.The results showed that the satisfaction levels from high to low are:tourism experience,tourism attractions,scenic area management,and tourism services.Therefore,satisfaction with related content under the service topic was the lowest so this aspect urgently needs to be improved and enhanced.
基金the National Natural Science Foundation of China (Grant No. 52472360)the China Postdoctoral Science Foundation (Grant No. 2023M7 30560)。
文摘The Safety Technical Specification for Electric Bicycles(GB 17761–2018, China) has been in effect for over six years, yet its influence on consumer purchase behaviour remains unclear. This study examines public perceptions of the specification and its impact on electric bicycle purchase decisions. Using Latent Dirichlet Allocation(LDA) to analyse 20, 971 social media comments, combined with sentiment analysis, a purchase behaviour model was developed. Additionally, 446 valid survey responses were analysed using Partial Least Squares Structural Equation Modelling to identify key influencing factors and their pathways. Bayesian network analysis was then employed to quantify the effects of these factors on purchase behaviour. The results reveal that attitudes and perceived safety are the most significant determinants of electric bicycle purchases. Furthermore, trust, perceived usefulness and face consciousness have a substantial influence on consumer attitudes. Regarding the specification's impact, the findings suggest that public trust and perception of the regulation positively contribute to purchase behaviour. This research provides a robust framework for understanding the drivers of electric bicycle purchase behaviour, supporting the sustainable and regulated growth of China's electric bicycle industry.
文摘With the rapid growth of online shopping platforms, more and more customers intend to share theirshopping experience and product reviews on the Internet. Both large quantity and various forms ofonline reviews bring difficulties for potential consumers to summary all the heterogenous reviews forreference. This paper proposes a new ranking method through online reviews based on differentaspects of the alternative products, which combines both objective and subjective sentiment values.Firstly, weights of these aspects are determined with LDA topic model to calculate the objectivesentiment value of the product. During this process, the realistic meaning of each aspect is alsosummarized. Then, consumers＇ personalized preferences are taken into consideration while calculatingtotal scores of alternative products. Meanwhile, comparative superiority between every two productsalso contributes to their final scores. Therefore, a directed graph model is constructed and the finalscore of each product is computed by improved PageRank algorithm. Finally, a case study is given toillustrate the feasibility and effectiveness of the proposed method. The result demonstrates that whileconsidering only objective sentiment values of the product, the ranking result obtained by our proposedmethod has a strong correlation with the actual sales orders. On the other hand, if consumers expresssubjective preferences towards a certain aspect, the final ranking is also consistent with the actualperformance of alternative products. It provides a new research idea for online customer review miningand personalized recommendation.
