Pub Date : 2022-08-01DOI: 10.1109/cost57098.2022.00048
Xinzhu Pu, Xinyue Xu
Social and technical transformations of the Internet have altered how digital games are produced, distributed, and played. However, studies argue for the significance of labor as an entry point to the analysis of digital game are mainly quantitative in approach, and the findings hardly go beyond the boundary of the game itself. The current academic researchers have not paid enough attention to the subject of game co-playing to investigate e-sports boosters’ digital labor. Through the research methods of participatory observation and in-depth interviews with 13 King of Glory boosters, this paper finds that the labor process of e-sports boosters, as a new professional group, is controlled by the dual digital logic of their hirer and the platform. It is suggested that in the platform economy, the digital logic is becoming a way of labor control, with a high degree of rigor, concealment and deceit, which exacerbates the asymmetry in the power relationship between online platforms and laborers.
{"title":"Playlabor: an Exploratory Study on Labor Control of E-Sports Boosters","authors":"Xinzhu Pu, Xinyue Xu","doi":"10.1109/cost57098.2022.00048","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00048","url":null,"abstract":"Social and technical transformations of the Internet have altered how digital games are produced, distributed, and played. However, studies argue for the significance of labor as an entry point to the analysis of digital game are mainly quantitative in approach, and the findings hardly go beyond the boundary of the game itself. The current academic researchers have not paid enough attention to the subject of game co-playing to investigate e-sports boosters’ digital labor. Through the research methods of participatory observation and in-depth interviews with 13 King of Glory boosters, this paper finds that the labor process of e-sports boosters, as a new professional group, is controlled by the dual digital logic of their hirer and the platform. It is suggested that in the platform economy, the digital logic is becoming a way of labor control, with a high degree of rigor, concealment and deceit, which exacerbates the asymmetry in the power relationship between online platforms and laborers.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132391368","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}
Pub Date : 2022-08-01DOI: 10.1109/CoST57098.2022.00083
Yingying Lv, Jingtao Wang, Wenbo Wu, Yun Pan
Bone age is the biological age that reflects the growth and development of human body. Bone age assessment has been applied and plays an important role in clinical medicine, sports science and justice. Reasonable convolution neural network (CNN) models can greatly improve the accuracy and efficiency of bone age assessment. By comparing various hand bone segmentation models trained by classical convolutional neural networks, we found that with intersection over inion (IoU) and dice similarity coefficient (Dice) as evaluation indexes, the segmentation model trained by U-Net had the best performance. Its IoU reached 0.9746, and its Dice reached 0.9871. This is contrary to our inherent recognition that the U-Net++ model is superior to the U-Net model. Based on the images segmented by U-Net, we applied five kinds of common convolutional neural networks to bone age prediction, with mean absolute error (MAE) and error accuracy within two years as evaluation indexes. The results showed that the MAE of Xception was 7.635 and the accuracy of errors within two years reached 97.59%. In this paper, we provide an optimal scheme for bone age image segmentation and bone age assessment, and provide a theoretical basis for the design of bone age assessment system.
骨龄是反映人体生长发育的生物年龄。骨龄评估在临床医学、体育科学和司法等领域都有广泛的应用和作用。合理的卷积神经网络(CNN)模型可以大大提高骨龄评估的准确性和效率。通过对比经典卷积神经网络训练的各种手骨分割模型，我们发现以交叉数(intersection over inion, IoU)和骰子相似系数(dice, dice)作为评价指标，U-Net训练的手骨分割模型表现最好。IoU为0.9746,Dice为0.9871。这与我们固有的认识相反，即unet++模型优于U-Net模型。在U-Net分割图像的基础上，应用5种常用卷积神经网络进行骨龄预测，以平均绝对误差(MAE)和2年内的误差精度为评价指标。结果表明:异常的MAE为7.635,2年内误差的准确率达到97.59%。本文提出了一种骨年龄图像分割和骨年龄评估的优化方案，为骨年龄评估系统的设计提供了理论依据。
{"title":"Performance comparison of deep learning methods on hand bone segmentation and bone age assessment","authors":"Yingying Lv, Jingtao Wang, Wenbo Wu, Yun Pan","doi":"10.1109/CoST57098.2022.00083","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00083","url":null,"abstract":"Bone age is the biological age that reflects the growth and development of human body. Bone age assessment has been applied and plays an important role in clinical medicine, sports science and justice. Reasonable convolution neural network (CNN) models can greatly improve the accuracy and efficiency of bone age assessment. By comparing various hand bone segmentation models trained by classical convolutional neural networks, we found that with intersection over inion (IoU) and dice similarity coefficient (Dice) as evaluation indexes, the segmentation model trained by U-Net had the best performance. Its IoU reached 0.9746, and its Dice reached 0.9871. This is contrary to our inherent recognition that the U-Net++ model is superior to the U-Net model. Based on the images segmented by U-Net, we applied five kinds of common convolutional neural networks to bone age prediction, with mean absolute error (MAE) and error accuracy within two years as evaluation indexes. The results showed that the MAE of Xception was 7.635 and the accuracy of errors within two years reached 97.59%. In this paper, we provide an optimal scheme for bone age image segmentation and bone age assessment, and provide a theoretical basis for the design of bone age assessment system.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114734140","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}
Time continuous emotion prediction problem has always been one of the difficulties in affective video content analysis. The current research mainly designs a temporally continuous long video emotion prediction method by dividing the long video into short video segments of fixed duration. These methods ignore the time dependencies between short video clips and the mood changes in short video clips. Therefore, combined with the related concepts of film and television narrative structure in cinematic language, this paper defines a prediction method for dimensional sentiment analysis of the movie and TV drama based on variable sequence length inputs. First, this paper defines a method for partitioning variable-length audiovisual sequences that set subunits of dimensional emotion prediction as variable sequence-length inputs. Then, a method for extracting and combining audio and visual features of each variable-length audiovisual sequence is proposed. Finally, a prediction network for dimensional emotion is designed based on variable sequence length inputs. This paper focuses on dimensional sentiment prediction and evaluates the proposed method on the extended COGNIMUSE dataset. The method achieves comparable performance to other methods while increasing the prediction speed, with the Mean Square Error (MSE) reduced from 0.13 to 0.11 for arousal and from 0.19 to 0.13 for valence.
{"title":"A Prediction Method for Dimensional Sentiment Analysis of the Movie and TV Drama based on Variable-length Sequence Input","authors":"Chunxiao Wang, Jingiing Zhang, Lihong Gan, Wei Jiang","doi":"10.1109/CoST57098.2022.00010","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00010","url":null,"abstract":"Time continuous emotion prediction problem has always been one of the difficulties in affective video content analysis. The current research mainly designs a temporally continuous long video emotion prediction method by dividing the long video into short video segments of fixed duration. These methods ignore the time dependencies between short video clips and the mood changes in short video clips. Therefore, combined with the related concepts of film and television narrative structure in cinematic language, this paper defines a prediction method for dimensional sentiment analysis of the movie and TV drama based on variable sequence length inputs. First, this paper defines a method for partitioning variable-length audiovisual sequences that set subunits of dimensional emotion prediction as variable sequence-length inputs. Then, a method for extracting and combining audio and visual features of each variable-length audiovisual sequence is proposed. Finally, a prediction network for dimensional emotion is designed based on variable sequence length inputs. This paper focuses on dimensional sentiment prediction and evaluates the proposed method on the extended COGNIMUSE dataset. The method achieves comparable performance to other methods while increasing the prediction speed, with the Mean Square Error (MSE) reduced from 0.13 to 0.11 for arousal and from 0.19 to 0.13 for valence.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116708025","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}
Pub Date : 2022-08-01DOI: 10.1109/CoST57098.2022.00072
Qi Zhao, Yiqing Hu, Zhenyu Pang, Derong Ren
Low earth orbit (LEO) satellite networks can provide global broadband access services and thus are complementary to current terrestrial mobile communication systems. The limited resources of LEO satellite platform and the uneven distribution of ground services bring many challenges to the design of satellite ground access scheme. The beam hopping (BH) technology meets the non-uniform and dynamic service requirements of users through time slicing technology, and enhances the resource utilization and service capability of satellites. However, the application of BH technology in LEO satellites is facing many challenges. This paper analyzes and considers from the system and technical aspects, combs and analyzes its research work. Finally, the development trend of BH system is given, which provides an idea for the application and development of BH technology for LEO satellites.
{"title":"Beam Hopping for LEO Satellite:Challenges and Opportunities","authors":"Qi Zhao, Yiqing Hu, Zhenyu Pang, Derong Ren","doi":"10.1109/CoST57098.2022.00072","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00072","url":null,"abstract":"Low earth orbit (LEO) satellite networks can provide global broadband access services and thus are complementary to current terrestrial mobile communication systems. The limited resources of LEO satellite platform and the uneven distribution of ground services bring many challenges to the design of satellite ground access scheme. The beam hopping (BH) technology meets the non-uniform and dynamic service requirements of users through time slicing technology, and enhances the resource utilization and service capability of satellites. However, the application of BH technology in LEO satellites is facing many challenges. This paper analyzes and considers from the system and technical aspects, combs and analyzes its research work. Finally, the development trend of BH system is given, which provides an idea for the application and development of BH technology for LEO satellites.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131010142","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}
Pub Date : 2022-08-01DOI: 10.1109/CoST57098.2022.00092
Yubo Deng, Jiachuan He, Fangping Yang, Yi Yang, Zihan Ke
In recent years, the reservation data of scenic spots in Gansu Province has increased dramatically. This paper cleans and integrates these scattered data, refines the correlation relationship between them, constructs a relationship map, and inputs it into the constructed recommendation system, in order to achieve the accurate recommendation for tourists to reserve scenic spots. Firstly, this paper constructs the relationship map between tourists’ characteristics and scenic spots based on the real data of scenic spots reservation in Gansu Province. Next, the paper divides the data set into training set and test set to train the model of recall algorithm. Then, the paper compares the clustering effect of different clustering algorithms to find out the most efficient algorithm to get Top-N recommendation. Finally, this paper uses two sorting algorithms to sort the scenic spots in the recommendation list respectively, and thus achieve the scenic spot recommendation for tourists.
{"title":"Analysis and application of reservation of scenic spot based on relationship graph","authors":"Yubo Deng, Jiachuan He, Fangping Yang, Yi Yang, Zihan Ke","doi":"10.1109/CoST57098.2022.00092","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00092","url":null,"abstract":"In recent years, the reservation data of scenic spots in Gansu Province has increased dramatically. This paper cleans and integrates these scattered data, refines the correlation relationship between them, constructs a relationship map, and inputs it into the constructed recommendation system, in order to achieve the accurate recommendation for tourists to reserve scenic spots. Firstly, this paper constructs the relationship map between tourists’ characteristics and scenic spots based on the real data of scenic spots reservation in Gansu Province. Next, the paper divides the data set into training set and test set to train the model of recall algorithm. Then, the paper compares the clustering effect of different clustering algorithms to find out the most efficient algorithm to get Top-N recommendation. Finally, this paper uses two sorting algorithms to sort the scenic spots in the recommendation list respectively, and thus achieve the scenic spot recommendation for tourists.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127431465","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}
Pub Date : 2022-08-01DOI: 10.1109/CoST57098.2022.00026
Shouzhi Sun, Jiali Wang, Zheng Gong, Aiping Tan, Yan Wang
Knowledge extraction is the core work of constructing a knowledge graph, but most knowledge extraction methods assume perfect data support. Therefore, this paper analyzes the characteristics of big data in the cultural industry. In addition to the consensus characteristics of big data, these data also highlight the features of sectors such as low resources and intense data boundary fuzziness. Therefore, this paper proposes a knowledge extraction method for cultural industry data (CT-DA). Firstly, design a labeling strategy for big data in the cultural industry. Secondly, according to the low resource characteristics of data, create the counter transfer learning layer to realize resource transfer. Considering the intense fuzziness of data, design the dynamic attention mechanism layer for learning the critical attention of entities in the cultural field. Finally, build an experimental platform. The experiments show that this method has performance advantages in accuracy, recall, and F1.
{"title":"CT-DA: A Knowledge Extraction Method for Cultural Industry Big Data","authors":"Shouzhi Sun, Jiali Wang, Zheng Gong, Aiping Tan, Yan Wang","doi":"10.1109/CoST57098.2022.00026","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00026","url":null,"abstract":"Knowledge extraction is the core work of constructing a knowledge graph, but most knowledge extraction methods assume perfect data support. Therefore, this paper analyzes the characteristics of big data in the cultural industry. In addition to the consensus characteristics of big data, these data also highlight the features of sectors such as low resources and intense data boundary fuzziness. Therefore, this paper proposes a knowledge extraction method for cultural industry data (CT-DA). Firstly, design a labeling strategy for big data in the cultural industry. Secondly, according to the low resource characteristics of data, create the counter transfer learning layer to realize resource transfer. Considering the intense fuzziness of data, design the dynamic attention mechanism layer for learning the critical attention of entities in the cultural field. Finally, build an experimental platform. The experiments show that this method has performance advantages in accuracy, recall, and F1.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122374321","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}
Pub Date : 2022-08-01DOI: 10.1109/cost57098.2022.00076
Luqing Wang, Ruicheng Liu
The e-commerce live-streaming has been developing rapidly, and the beauty industry has become the industry most deeply affected by it. Based on SOR model, this paper introduces consumer trust theory and affective commitment theory, summarizes the characteristics of beauty live stream into three dimensions, namely live streamer attractiveness, brand awareness and product discount, collects data through questionnaires and analyzes the influence of live streamer and product on consumers’ purchase intention, in order to find out how the characteristics of beauty live stream affect consumers’ purchase intention. And finally based on conclusions, put forward countermeasures and suggestions to optimize the effect of beauty live stream from two aspects of live streamers and brands, which is of great significance to enrich the theoretical research and practice in the field of e-commerce live-streaming.
{"title":"Research on the Influence of Beauty Live Stream on Consumers’ Purchase Intention","authors":"Luqing Wang, Ruicheng Liu","doi":"10.1109/cost57098.2022.00076","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00076","url":null,"abstract":"The e-commerce live-streaming has been developing rapidly, and the beauty industry has become the industry most deeply affected by it. Based on SOR model, this paper introduces consumer trust theory and affective commitment theory, summarizes the characteristics of beauty live stream into three dimensions, namely live streamer attractiveness, brand awareness and product discount, collects data through questionnaires and analyzes the influence of live streamer and product on consumers’ purchase intention, in order to find out how the characteristics of beauty live stream affect consumers’ purchase intention. And finally based on conclusions, put forward countermeasures and suggestions to optimize the effect of beauty live stream from two aspects of live streamers and brands, which is of great significance to enrich the theoretical research and practice in the field of e-commerce live-streaming.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121459372","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}
Pub Date : 2022-08-01DOI: 10.1109/CoST57098.2022.00070
Ling Lei, Y. Liang, Xiaojian Zhang
Interaction can not only capture users’ attention, but also improve the efficiency of users’ acquisition of information, which is today’s important way of communication. Dunhuang culture as an important traditional Chinese culture has returned to people’s field of vision in recent years, but people are also faced with challenges of integrating interaction into Dunhuang culture for better understanding and transmission. This paper explored a brand new interaction design on Dunhuang culture by developing an interactive game themed on Dunhuang culture based on Unity Engine. The game is positioned as an interactive storybook to cater to the development direction of cultural products and meet the actual interaction needs of the audience while transmitting Dunhuang culture.
{"title":"Research and Implementation of Interaction Design on Dunhuang Culture","authors":"Ling Lei, Y. Liang, Xiaojian Zhang","doi":"10.1109/CoST57098.2022.00070","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00070","url":null,"abstract":"Interaction can not only capture users’ attention, but also improve the efficiency of users’ acquisition of information, which is today’s important way of communication. Dunhuang culture as an important traditional Chinese culture has returned to people’s field of vision in recent years, but people are also faced with challenges of integrating interaction into Dunhuang culture for better understanding and transmission. This paper explored a brand new interaction design on Dunhuang culture by developing an interactive game themed on Dunhuang culture based on Unity Engine. The game is positioned as an interactive storybook to cater to the development direction of cultural products and meet the actual interaction needs of the audience while transmitting Dunhuang culture.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"1883 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128704436","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}
Pub Date : 2022-08-01DOI: 10.1109/cost57098.2022.00018
Haoqi Sun, Ning Luo, Li-juan Zhou, Songwei Wei
With the popularization and development of the Internet, text information has shown an exponential growth trend. This information overload phenomenon affects the ability of users to receive critical information, and people’s demand for quick access to information is increasing. Text summarization technology uses computers to automatically extract the key information of text, which helps to grasp the text content accurately and quickly, so it has a good application prospect. The traditional rule-based method simply counts the word frequency and lacks the consideration of the semantic information of the text, so the results are not accurate enough. To this end, this paper proposes an extractive text summarization algorithm based on multiple feature weighting, which comprehensively considers the global information, surface information, structural information, and semantic information of the text by weighting the sentence position, the total amount of keyword information, keyword distribution, and semantic similarity. This method retains the advantages of the rule-based approach from not requiring data annotation and saving computational resources while improving the text understanding capability of the model. Experimental results show that the model improves the evaluation results of the datasets, improving the quality and accuracy of text summarization. And when the model is applied to the text processing system, the user can quickly obtain the required information, effectively speeding up the process of obtaining and processing information.
{"title":"Design and Implementation of Text Processing System Based on Summarization Algorithm","authors":"Haoqi Sun, Ning Luo, Li-juan Zhou, Songwei Wei","doi":"10.1109/cost57098.2022.00018","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00018","url":null,"abstract":"With the popularization and development of the Internet, text information has shown an exponential growth trend. This information overload phenomenon affects the ability of users to receive critical information, and people’s demand for quick access to information is increasing. Text summarization technology uses computers to automatically extract the key information of text, which helps to grasp the text content accurately and quickly, so it has a good application prospect. The traditional rule-based method simply counts the word frequency and lacks the consideration of the semantic information of the text, so the results are not accurate enough. To this end, this paper proposes an extractive text summarization algorithm based on multiple feature weighting, which comprehensively considers the global information, surface information, structural information, and semantic information of the text by weighting the sentence position, the total amount of keyword information, keyword distribution, and semantic similarity. This method retains the advantages of the rule-based approach from not requiring data annotation and saving computational resources while improving the text understanding capability of the model. Experimental results show that the model improves the evaluation results of the datasets, improving the quality and accuracy of text summarization. And when the model is applied to the text processing system, the user can quickly obtain the required information, effectively speeding up the process of obtaining and processing information.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115399965","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}
Pub Date : 2022-08-01DOI: 10.1109/cost57098.2022.00024
Wenheng Sun, Wan Qiu, Xiaojia Huang, Jianming Hu, Tianyuan Wu
This paper analyzes the influencing factors of tourism development through the emotional tendencies in online travel reviews, and uses a Bidirectional long short-term memory Convolutional Neural Network (BiLSTM-CNN) deep learning model to classify online travel reviews. The model has high accuracy and good loss function convergence. Then we use the Dynamic Topic Models (DTM) model to analyze the classified texts at two levels. At the micro level, the main influencing factors of a destination are obtained for a certain destination, and corresponding improvement plans are proposed for the negative influencing factors. At the macro level, this paper analyzes the changing trend of the destination’s emotional inclination under the two influencing factors of fare and traffic.
{"title":"Analysis of Emotional Influencing Factors of Online Travel Reviews Based on BiLSTM-CNN","authors":"Wenheng Sun, Wan Qiu, Xiaojia Huang, Jianming Hu, Tianyuan Wu","doi":"10.1109/cost57098.2022.00024","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00024","url":null,"abstract":"This paper analyzes the influencing factors of tourism development through the emotional tendencies in online travel reviews, and uses a Bidirectional long short-term memory Convolutional Neural Network (BiLSTM-CNN) deep learning model to classify online travel reviews. The model has high accuracy and good loss function convergence. Then we use the Dynamic Topic Models (DTM) model to analyze the classified texts at two levels. At the micro level, the main influencing factors of a destination are obtained for a certain destination, and corresponding improvement plans are proposed for the negative influencing factors. At the macro level, this paper analyzes the changing trend of the destination’s emotional inclination under the two influencing factors of fare and traffic.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114481833","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：