By virtue of the low-cost and high-efficiency internet traffic monetizing ability,key opinion leaders(KOL)have achieved great success on social media platforms in terms of agricultural brand e-commerce marketing.Howev...By virtue of the low-cost and high-efficiency internet traffic monetizing ability,key opinion leaders(KOL)have achieved great success on social media platforms in terms of agricultural brand e-commerce marketing.However,opinion leaders tend to adopt different promotion strategies according to their preference to brands.How to optimize online marketing strategies based on the difference in opinion leaders’attitudes remains a problem demanding prompt solution for agricultural product brand enterprises.This study takes agricultural product brand enterprises and opinion leaders with limited rationality as the research subjects.On the premise of considering the difference in opinion leaders’attitudes towards brands,the paper combines the evolutionary game theory to construct agricultural product brands’online promotion strategy evolutionary model,adopts visualization system to simulate the evolutionary process of brand online promotion strategies,verifies model validity and explores the influencing mechanism of punishment on opinion leaders’negative promotion.Results of multi-agent-based simulation demonstrate that investment in brand promotion,irrelevant to opinion leaders’attitudes towards brands,pertains to the absolute advantage strategy of agricultural product brand enterprises.Reinforced intensity of punishment against opinion leaders following negative promotion may change opinion leaders’promotion strategies for agricultural product brands.Moreover,the present study provides an idea and reference to the management decisions of agricultural product brand enterprises’online brand promotion strategies.展开更多
With the eruption of big data,practical recommendation schemes are now very important in various fields,including e-commerce,social networks,and a number of web-based services.Nowadays,there exist many personalized mo...With the eruption of big data,practical recommendation schemes are now very important in various fields,including e-commerce,social networks,and a number of web-based services.Nowadays,there exist many personalized movie recommendation schemes utilizing publicly available movie datasets(e.g.,MovieLens and Netflix),and returning improved performance metrics(e.g.,Root-Mean-Square Error(RMSE)).However,two fundamental issues faced by movie recommendation systems are still neglected:first,scalability,and second,practical usage feedback and verification based on real implementation.In particular,Collaborative Filtering(CF)is one of the major prevailing techniques for implementing recommendation systems.However,traditional CF schemes suffer from a time complexity problem,which makes them bad candidates for real-world recommendation systems.In this paper,we address these two issues.Firstly,a simple but high-efficient recommendation algorithm is proposed,which exploits users1 profile attributes to partition them into several clusters.For each cluster,a virtual opinion leader is conceived to represent the whole cluster,such that the dimension of the original useritem matrix can be significantly reduced,then a Weighted Slope One-VU method is designed and applied to the virtual opinion leader-item matrix to obtain the recommendation results.Compared to traditional clusteringbased CF recommendation schemes,our method can significantly reduce the time complexity,while achieving comparable recommendation performance.Furthermore,we have constructed a real personalized web-based movie recommendation system,MovieWatch,opened it to the public,collected user feedback on recommendations,and evaluated the feasibility and accuracy of our system based on this real-world data.展开更多
基金supported by the National Key R&D Program of China(2017YFB1400500)the Project of Promoting the Connotative Development of Beijing Information S&T University(521201090A,5026010961).
文摘By virtue of the low-cost and high-efficiency internet traffic monetizing ability,key opinion leaders(KOL)have achieved great success on social media platforms in terms of agricultural brand e-commerce marketing.However,opinion leaders tend to adopt different promotion strategies according to their preference to brands.How to optimize online marketing strategies based on the difference in opinion leaders’attitudes remains a problem demanding prompt solution for agricultural product brand enterprises.This study takes agricultural product brand enterprises and opinion leaders with limited rationality as the research subjects.On the premise of considering the difference in opinion leaders’attitudes towards brands,the paper combines the evolutionary game theory to construct agricultural product brands’online promotion strategy evolutionary model,adopts visualization system to simulate the evolutionary process of brand online promotion strategies,verifies model validity and explores the influencing mechanism of punishment on opinion leaders’negative promotion.Results of multi-agent-based simulation demonstrate that investment in brand promotion,irrelevant to opinion leaders’attitudes towards brands,pertains to the absolute advantage strategy of agricultural product brand enterprises.Reinforced intensity of punishment against opinion leaders following negative promotion may change opinion leaders’promotion strategies for agricultural product brands.Moreover,the present study provides an idea and reference to the management decisions of agricultural product brand enterprises’online brand promotion strategies.
文摘With the eruption of big data,practical recommendation schemes are now very important in various fields,including e-commerce,social networks,and a number of web-based services.Nowadays,there exist many personalized movie recommendation schemes utilizing publicly available movie datasets(e.g.,MovieLens and Netflix),and returning improved performance metrics(e.g.,Root-Mean-Square Error(RMSE)).However,two fundamental issues faced by movie recommendation systems are still neglected:first,scalability,and second,practical usage feedback and verification based on real implementation.In particular,Collaborative Filtering(CF)is one of the major prevailing techniques for implementing recommendation systems.However,traditional CF schemes suffer from a time complexity problem,which makes them bad candidates for real-world recommendation systems.In this paper,we address these two issues.Firstly,a simple but high-efficient recommendation algorithm is proposed,which exploits users1 profile attributes to partition them into several clusters.For each cluster,a virtual opinion leader is conceived to represent the whole cluster,such that the dimension of the original useritem matrix can be significantly reduced,then a Weighted Slope One-VU method is designed and applied to the virtual opinion leader-item matrix to obtain the recommendation results.Compared to traditional clusteringbased CF recommendation schemes,our method can significantly reduce the time complexity,while achieving comparable recommendation performance.Furthermore,we have constructed a real personalized web-based movie recommendation system,MovieWatch,opened it to the public,collected user feedback on recommendations,and evaluated the feasibility and accuracy of our system based on this real-world data.
