Rural tourism plays a crucial role in driving the sustainable development of rural economies.With the rise of the digital economy,user-generated content(UGC)videos on platforms such as TikTok have become a significant...Rural tourism plays a crucial role in driving the sustainable development of rural economies.With the rise of the digital economy,user-generated content(UGC)videos on platforms such as TikTok have become a significant factor influencing consumer decision-making,creating new opportunities for the growth of rural tourism.Using the TikTok app as the research platform,this study examines the relationship between UGC short videos,tourists’intentions to engage in rural tourism,and their perception of destination image.Specifically,it explores the impact of UGC short videos on tourists’willingness to participate in rural tourism and the mediating role of destination image perception.The findings indicate that UGC short videos positively influence tourists’willingness to engage in rural tourism.Destination image perception mediates this relationship,shaping tourists’decisions through cognitive and emotional image perceptions.Based on these findings,this paper recommends rural tourism destination managers enhance promotional strategies and improve destination image perception through UGC short video content.展开更多
User-generated content(UGC) such as blogs and twitters are exploding in modern Internet services. In such systems, recommender systems are needed to help people filter vast amount of UGC generated by other users. Howe...User-generated content(UGC) such as blogs and twitters are exploding in modern Internet services. In such systems, recommender systems are needed to help people filter vast amount of UGC generated by other users. However, traditional recommendation models do not use user authorship of items. In this paper, we show that with this additional information, we can significantly improve the performance of recommendations. A generative model that combines hierarchical topic modeling and matrix factorization is proposed. Empirical results show that our model outperforms other state-of-the-art models, and can provide interpretable topic structures for users and items. Furthermore, since user interests can be inferred from their productions, recommendations can be made for users that do not have any ratings to solve the cold-start problem.展开更多
In the rapidly evolving landscape of natural language processing(NLP)and sentiment analysis,improving the accuracy and efficiency of sentiment classification models is crucial.This paper investigates the performance o...In the rapidly evolving landscape of natural language processing(NLP)and sentiment analysis,improving the accuracy and efficiency of sentiment classification models is crucial.This paper investigates the performance of two advanced models,the Large Language Model(LLM)LLaMA model and NLP BERT model,in the context of airline review sentiment analysis.Through fine-tuning,domain adaptation,and the application of few-shot learning,the study addresses the subtleties of sentiment expressions in airline-related text data.Employing predictive modeling and comparative analysis,the research evaluates the effectiveness of Large Language Model Meta AI(LLaMA)and Bidirectional Encoder Representations from Transformers(BERT)in capturing sentiment intricacies.Fine-tuning,including domain adaptation,enhances the models'performance in sentiment classification tasks.Additionally,the study explores the potential of few-shot learning to improve model generalization using minimal annotated data for targeted sentiment analysis.By conducting experiments on a diverse airline review dataset,the research quantifies the impact of fine-tuning,domain adaptation,and few-shot learning on model performance,providing valuable insights for industries aiming to predict recommendations and enhance customer satisfaction through a deeper understanding of sentiment in user-generated content(UGC).This research contributes to refining sentiment analysis models,ultimately fostering improved customer satisfaction in the airline industry.展开更多
Drone technology opens the door to major changes and opportunities in our society.But this technology,like many others,needs to be administered and regulated to prevent potential harm to the public.Therefore,national ...Drone technology opens the door to major changes and opportunities in our society.But this technology,like many others,needs to be administered and regulated to prevent potential harm to the public.Therefore,national and local governments around the world established regulations for operating drones,which bans drone use from specific locations or limits their operation to qualified drone pilots only.This study reviews the types of restrictions on drone use that are specified in federal drone regulations for the US,the UK,and France,and in state regulations for the US.The study also maps restricted areas and assesses compliance with these regulations by analyzing the spatial contribution patterns to three crowd-sourced drone portals,namely SkyPixel,Flickr,and DroneSpot,relative to restricted areas.The analysis is performed both at the national level and at the state/regional level within each of the three countries,where statistical tests are conducted to compare compliance rates between the three drone portals.This study provides new insight into drone users’awareness of and compliance with drone regulations.This can help governments to tailor information campaigns for increased awareness of drone regulations among drone users and to determine where increased control and enforcement of drone regulations is necessary.展开更多
This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to use...This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.展开更多
Recently,there has been an unprecedented high cost of living,widespread frustration,and discontent among Nigerians who attribute their experiences to the high-handed leadership style of President Bola Ahmed Tinubu(PBA...Recently,there has been an unprecedented high cost of living,widespread frustration,and discontent among Nigerians who attribute their experiences to the high-handed leadership style of President Bola Ahmed Tinubu(PBAT),popularly calledÈmi lókàn.To mitigate the arduous experiences and emotional stress caused by PBAT’s impromptu stringent policies and self-imposed exchange rate brouhaha,individuals seek out social media platforms with user-generated humorous memes(HMs).This study,cast in the interpersonal theory of multimodality,multimodality,and uses and gratification theory,investigates how HMs are deployed as resources to evaluate themes that project indices of economic downturn in Nigeria.The data for the study comprises eighteen(18)purposively selected online memes analyzed by deploying theoretical concepts that are symbolic,interactional,analytic,reactional,etc.,to interpret the memes both in isolation and as ensembles.Eleven thematic classes of memes that project and accentuate current harsh economic realities were categorized.The study posits that memes evoke distinct reactions,which positively signal intersubjective engagements on the economic downturn,and do not only serve for humor but also to mitigate shared experiences,propagate public aware-ness,castigate and satirize government’s ineptitude,help users to make important lifestyle changes,and find moments of levity in adversity.展开更多
Nowadays,user-generated content is pivotal for many companies:people trust other customers’opinions more than any brand advertisement.Brands are aware of this and try to promote and motivate their customers to create...Nowadays,user-generated content is pivotal for many companies:people trust other customers’opinions more than any brand advertisement.Brands are aware of this and try to promote and motivate their customers to create high-quality content.However,this way of operating is still at an early stage:there is a lack of fairness,as companies typically do not provide a validation system,or if they do,it is not based on a transparent solution,and often,there is no reward for creating unique and high-quality content.In this paper,we focus on the problem of incentivizing users’creation of content in the form of customer reviews in the online grocery industry.Specifically,we illustrate the solution to the problem devised in the Re-Taled project by relying on blockchain technology.We develop a decentralized ecosystem of consumers,influencers,and manufacturers,where content creators are rewarded for their contribution according to a framework that provides incentives in the form of both reputation and monetization.Blockchain technology is used to certify the content’s authenticity and compensate content creators with a cryptographic token.We illustrate the technical choices of the solution together with its software architecture and implemented platform.In particular,we introduce the framework used to validate the trustworthiness of user-generated content and favor fairness and transparency within the platform.展开更多
In the era of information explosion,short videos have experienced explosive growth,broadly categorized into two forms:long videos and short videos,differentiated by duration and information content.Long videos general...In the era of information explosion,short videos have experienced explosive growth,broadly categorized into two forms:long videos and short videos,differentiated by duration and information content.Long videos generally carry a higher information load and have a longer duration,while short videos are characterized by their brief duration and relatively lower information content.As the industry has evolved,with both long and short videos becoming key entry points for traffic,videos have undergone a simplistic classification leading to a coarse differentiation of audience groups.Examples include platforms like Douyin,Bilibili,Youku,iQiyi,Tencent,among others.User-Generated Content(UGC),primarily in the form of short videos,serves as the main framework where users spontaneously create and upload content to platforms.These platforms utilize a"decentralized"algorithm to drive traffic,creating new entry points.UGC is characterized by low cost,down-to-earth content,authenticity,minimal information load,and strong interactive elements.However,with the emergence of competition,since 2019,platforms have witnessed the rise of a considerable number of"pseudo-UGC"production models through information flow advertising.Many Multi-Channel Networks(MCNs)have entered the scene,using"pseudo-UGC"methods for video marketing,giving rise to a new wave of"short video teams."These teams consist predominantly of internet dramas,variety shows,and spontaneously formed groups,shaping a diverse landscape of"innovative short video production methods."展开更多
The study of tourism destination images is of great significance in the tourism discipline.Tourism user-generated content(UGC),i.e.,the feedback on tourism websites,provides rich information for constructing a destina...The study of tourism destination images is of great significance in the tourism discipline.Tourism user-generated content(UGC),i.e.,the feedback on tourism websites,provides rich information for constructing a destination image.However,it is difficult for tourism researchers to obtain a relatively complete and intuitive destination image due to the unintuitive destination image display,the significant variance in departure time and data length,and the destination type in UGC.We propose TDIVis,a carefully designed visual analytics system,aimed at obtaining a relatively comprehensive destination image.Specifically,a keyword-based sentiment visualization method is proposed to associate the cognitive image with the emotional image,and by this method,both time evolution analysis and classification analysis are considered;a multi-attribute association double sequence visualization method is proposed to associate two different types of text sequences and provide a dynamic visual encoding interaction method for the multi-attribute characteristics of sequences.The effectiveness and usability of TDIVis are demonstrated through four cases and a user study.展开更多
Abundant tourism user-generated content(UGC)contains a wealth of cognitive and emotional in-formation,providing valuable data for building destination images that depict tourists’experiences and appraisal of the dest...Abundant tourism user-generated content(UGC)contains a wealth of cognitive and emotional in-formation,providing valuable data for building destination images that depict tourists’experiences and appraisal of the destinations during the tours.In particular,multiple destination images can assist tourism managers in exploring the commonalities and differences to investigate the elements of interest of tourists and improve the competitiveness of the destinations.However,existing methods usually focus on the image of a single destination,and they are not adequate to analyze and visualize UGC to extract valuable information and knowledge.Therefore,we discuss requirements with tourism experts and present MDIVis,a multi-level interactive visual analytics system that allows analysts to comprehend and analyze the cognitive themes and emotional experiences of multiple destination images for comparison.Specifically,we design a novel sentiment matrix view to summarize multiple destination images and improve two classic views to analyze the time-series pattern and compare the detailed information of images.Finally,we demonstrate the utility of MDIVis through three case studies with domain experts on real-world data,and the usability and effectiveness are confirmed through expert interviews.展开更多
基金The Liaoning Provincial Social Science Planning Fund Project(L23CGL002)。
文摘Rural tourism plays a crucial role in driving the sustainable development of rural economies.With the rise of the digital economy,user-generated content(UGC)videos on platforms such as TikTok have become a significant factor influencing consumer decision-making,creating new opportunities for the growth of rural tourism.Using the TikTok app as the research platform,this study examines the relationship between UGC short videos,tourists’intentions to engage in rural tourism,and their perception of destination image.Specifically,it explores the impact of UGC short videos on tourists’willingness to participate in rural tourism and the mediating role of destination image perception.The findings indicate that UGC short videos positively influence tourists’willingness to engage in rural tourism.Destination image perception mediates this relationship,shaping tourists’decisions through cognitive and emotional image perceptions.Based on these findings,this paper recommends rural tourism destination managers enhance promotional strategies and improve destination image perception through UGC short video content.
基金Project supported by the Monitoring Statistics Project on Agricultural and Rural Resources,MOA,Chinathe Innovative Talents Project,MOA,Chinathe Science and Technology Innovation Project Fund of Chinese Academy of Agricultural Sciences(No.CAAS-ASTIP-2015-AI I-02)
文摘User-generated content(UGC) such as blogs and twitters are exploding in modern Internet services. In such systems, recommender systems are needed to help people filter vast amount of UGC generated by other users. However, traditional recommendation models do not use user authorship of items. In this paper, we show that with this additional information, we can significantly improve the performance of recommendations. A generative model that combines hierarchical topic modeling and matrix factorization is proposed. Empirical results show that our model outperforms other state-of-the-art models, and can provide interpretable topic structures for users and items. Furthermore, since user interests can be inferred from their productions, recommendations can be made for users that do not have any ratings to solve the cold-start problem.
文摘In the rapidly evolving landscape of natural language processing(NLP)and sentiment analysis,improving the accuracy and efficiency of sentiment classification models is crucial.This paper investigates the performance of two advanced models,the Large Language Model(LLM)LLaMA model and NLP BERT model,in the context of airline review sentiment analysis.Through fine-tuning,domain adaptation,and the application of few-shot learning,the study addresses the subtleties of sentiment expressions in airline-related text data.Employing predictive modeling and comparative analysis,the research evaluates the effectiveness of Large Language Model Meta AI(LLaMA)and Bidirectional Encoder Representations from Transformers(BERT)in capturing sentiment intricacies.Fine-tuning,including domain adaptation,enhances the models'performance in sentiment classification tasks.Additionally,the study explores the potential of few-shot learning to improve model generalization using minimal annotated data for targeted sentiment analysis.By conducting experiments on a diverse airline review dataset,the research quantifies the impact of fine-tuning,domain adaptation,and few-shot learning on model performance,providing valuable insights for industries aiming to predict recommendations and enhance customer satisfaction through a deeper understanding of sentiment in user-generated content(UGC).This research contributes to refining sentiment analysis models,ultimately fostering improved customer satisfaction in the airline industry.
文摘Drone technology opens the door to major changes and opportunities in our society.But this technology,like many others,needs to be administered and regulated to prevent potential harm to the public.Therefore,national and local governments around the world established regulations for operating drones,which bans drone use from specific locations or limits their operation to qualified drone pilots only.This study reviews the types of restrictions on drone use that are specified in federal drone regulations for the US,the UK,and France,and in state regulations for the US.The study also maps restricted areas and assesses compliance with these regulations by analyzing the spatial contribution patterns to three crowd-sourced drone portals,namely SkyPixel,Flickr,and DroneSpot,relative to restricted areas.The analysis is performed both at the national level and at the state/regional level within each of the three countries,where statistical tests are conducted to compare compliance rates between the three drone portals.This study provides new insight into drone users’awareness of and compliance with drone regulations.This can help governments to tailor information campaigns for increased awareness of drone regulations among drone users and to determine where increased control and enforcement of drone regulations is necessary.
基金funded by the Office of the Vice-President for Research and Development of Cebu Technological University.
文摘This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.
文摘Recently,there has been an unprecedented high cost of living,widespread frustration,and discontent among Nigerians who attribute their experiences to the high-handed leadership style of President Bola Ahmed Tinubu(PBAT),popularly calledÈmi lókàn.To mitigate the arduous experiences and emotional stress caused by PBAT’s impromptu stringent policies and self-imposed exchange rate brouhaha,individuals seek out social media platforms with user-generated humorous memes(HMs).This study,cast in the interpersonal theory of multimodality,multimodality,and uses and gratification theory,investigates how HMs are deployed as resources to evaluate themes that project indices of economic downturn in Nigeria.The data for the study comprises eighteen(18)purposively selected online memes analyzed by deploying theoretical concepts that are symbolic,interactional,analytic,reactional,etc.,to interpret the memes both in isolation and as ensembles.Eleven thematic classes of memes that project and accentuate current harsh economic realities were categorized.The study posits that memes evoke distinct reactions,which positively signal intersubjective engagements on the economic downturn,and do not only serve for humor but also to mitigate shared experiences,propagate public aware-ness,castigate and satirize government’s ineptitude,help users to make important lifestyle changes,and find moments of levity in adversity.
基金supported by the project SERICS(PE00000014)under the NRRP MUR program funded by the EU-NextGenerationEU,and the project Re-Taled(957228)funded by NGI TruBlo.
文摘Nowadays,user-generated content is pivotal for many companies:people trust other customers’opinions more than any brand advertisement.Brands are aware of this and try to promote and motivate their customers to create high-quality content.However,this way of operating is still at an early stage:there is a lack of fairness,as companies typically do not provide a validation system,or if they do,it is not based on a transparent solution,and often,there is no reward for creating unique and high-quality content.In this paper,we focus on the problem of incentivizing users’creation of content in the form of customer reviews in the online grocery industry.Specifically,we illustrate the solution to the problem devised in the Re-Taled project by relying on blockchain technology.We develop a decentralized ecosystem of consumers,influencers,and manufacturers,where content creators are rewarded for their contribution according to a framework that provides incentives in the form of both reputation and monetization.Blockchain technology is used to certify the content’s authenticity and compensate content creators with a cryptographic token.We illustrate the technical choices of the solution together with its software architecture and implemented platform.In particular,we introduce the framework used to validate the trustworthiness of user-generated content and favor fairness and transparency within the platform.
文摘In the era of information explosion,short videos have experienced explosive growth,broadly categorized into two forms:long videos and short videos,differentiated by duration and information content.Long videos generally carry a higher information load and have a longer duration,while short videos are characterized by their brief duration and relatively lower information content.As the industry has evolved,with both long and short videos becoming key entry points for traffic,videos have undergone a simplistic classification leading to a coarse differentiation of audience groups.Examples include platforms like Douyin,Bilibili,Youku,iQiyi,Tencent,among others.User-Generated Content(UGC),primarily in the form of short videos,serves as the main framework where users spontaneously create and upload content to platforms.These platforms utilize a"decentralized"algorithm to drive traffic,creating new entry points.UGC is characterized by low cost,down-to-earth content,authenticity,minimal information load,and strong interactive elements.However,with the emergence of competition,since 2019,platforms have witnessed the rise of a considerable number of"pseudo-UGC"production models through information flow advertising.Many Multi-Channel Networks(MCNs)have entered the scene,using"pseudo-UGC"methods for video marketing,giving rise to a new wave of"short video teams."These teams consist predominantly of internet dramas,variety shows,and spontaneously formed groups,shaping a diverse landscape of"innovative short video production methods."
基金Project supported by the Science&Technology Department of Sichuan Province,China(No.2018GZ0171)the Chengdu Science and Technology Bureau,China(No.2015-HM01-00484-SF)。
文摘The study of tourism destination images is of great significance in the tourism discipline.Tourism user-generated content(UGC),i.e.,the feedback on tourism websites,provides rich information for constructing a destination image.However,it is difficult for tourism researchers to obtain a relatively complete and intuitive destination image due to the unintuitive destination image display,the significant variance in departure time and data length,and the destination type in UGC.We propose TDIVis,a carefully designed visual analytics system,aimed at obtaining a relatively comprehensive destination image.Specifically,a keyword-based sentiment visualization method is proposed to associate the cognitive image with the emotional image,and by this method,both time evolution analysis and classification analysis are considered;a multi-attribute association double sequence visualization method is proposed to associate two different types of text sequences and provide a dynamic visual encoding interaction method for the multi-attribute characteristics of sequences.The effectiveness and usability of TDIVis are demonstrated through four cases and a user study.
基金This work was supported by the Chengdu Science and Tech-nology Bureau,China(Grant No.2019-YF05-02121-SN).
文摘Abundant tourism user-generated content(UGC)contains a wealth of cognitive and emotional in-formation,providing valuable data for building destination images that depict tourists’experiences and appraisal of the destinations during the tours.In particular,multiple destination images can assist tourism managers in exploring the commonalities and differences to investigate the elements of interest of tourists and improve the competitiveness of the destinations.However,existing methods usually focus on the image of a single destination,and they are not adequate to analyze and visualize UGC to extract valuable information and knowledge.Therefore,we discuss requirements with tourism experts and present MDIVis,a multi-level interactive visual analytics system that allows analysts to comprehend and analyze the cognitive themes and emotional experiences of multiple destination images for comparison.Specifically,we design a novel sentiment matrix view to summarize multiple destination images and improve two classic views to analyze the time-series pattern and compare the detailed information of images.Finally,we demonstrate the utility of MDIVis through three case studies with domain experts on real-world data,and the usability and effectiveness are confirmed through expert interviews.
