{"title":"Visualization of POI Competitiveness Using Extracted Map Tiles from Social Media Response Since COVID-19","authors":"Huaze Xie, Da Li, Yuanyuan Wang, Yukiko Kawai","doi":"10.1145/3486622.3493996","DOIUrl":"https://doi.org/10.1145/3486622.3493996","url":null,"abstract":"Since the spread of COVID-19 around the world, a series of policies and measures are adopted by the Japanese government to control the epidemic. As a result of these policies, people’s daily life and the functional division of society have changed. In order to understand the changes in urban function and people’s daily behavior over the past year, we collected and analyzed over 1.13 million social media data (Twitter in our example) containing geographic information. We propose regional competitiveness, which represents the access frequency of social data in each raster unit to several attributes. In order to analyze the regional competitiveness in different categories and map tiles, we applied an improved spatio-temporal graph attention network model (ST-GAT) based on unstructured POI (point of interest) data and Twitter data in different levels of the map to abstract the city-regional competitiveness. We have developed and evaluated the competitiveness map tiles based on 5 attributes utilized Twitter data at 2020 of Kyoto in Japan. As the spread of COVID-19 disease and government anti-epidemic measures change the frequency of visits to the core of the city and the trend of regional competitiveness, and our results showed that the regional competitiveness in the map tiles obtained by social media data and POI data visualizes the dynamic change analysis of crowd behavior activities and urban social functions. This research enlightens the promising future of spatio-temporal GAT in users’ dynamic responses with geographic information.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"41 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86243957","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}
Kenta Tsukatsune, Tatsuya Konishi, Yuto Mizutani, Mori Kurokawa, Shuichiro Haruta, T. Saito
{"title":"Does Activeness Originate in Individuals or Groups? Analysis of the Interrelationships between Network Indices and Posts Using Multilevel Cross-Lagged Model","authors":"Kenta Tsukatsune, Tatsuya Konishi, Yuto Mizutani, Mori Kurokawa, Shuichiro Haruta, T. Saito","doi":"10.1145/3498851.3498939","DOIUrl":"https://doi.org/10.1145/3498851.3498939","url":null,"abstract":"Web services allow users to send messages to each other. Thus, exploring the structural features of human networks that contribute to the increased activity of a service is both an academic question for researchers and a management interest for companies. However, some indices reflecting the characteristics of the network structure show the characteristics of individuals in the network, while others show those of the entire group (network). The analyst must understand these differences in characteristics before measuring the influence of indices on human activity. In addition, network indices are interrelated, and it is difficult to determine which index has the true causal effect. In this study, we select indices and apply a method that combines multilevel SEM (ML-SEM) and a cross-lagged model (CLM). Using Unipos data with network structures, we search for indices that affect monthly post frequency from among centrality and a scale-free index calculated based on an individual and a group, respectively. The results of our analysis show that closeness centrality has consistent and significant positive effects on post frequency in subsequent periods.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86247889","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}
Ewa Makowska-Tlomak, R. Nielek, Kinga H. Skorupska, Julia Paluch, Wiesław Kopeć
{"title":"Evaluating a Sentiment Analysis Tool to Detect Digital Transformation Stress","authors":"Ewa Makowska-Tlomak, R. Nielek, Kinga H. Skorupska, Julia Paluch, Wiesław Kopeć","doi":"10.1145/3486622.3494024","DOIUrl":"https://doi.org/10.1145/3486622.3494024","url":null,"abstract":"Digital transformation (DT) is the process of transformation of the business world with the use of information and communication technology (ICT) solutions. It not only has a large impact on organizations – their competitiveness and performance, but also on employee well-being and their stress levels. To measure the stress associated with such digital changes we used the concept of Digital Transformation Stress (DTS), and its verified psychometric survey-based tools. In this study we proposed and verified an alternative, automatic tool to measure DTS based on sentiment analysis of help desk ticket data set. First, we conducted sentiment analysis (SA) of help desk tickets of an international financial company to estimate how employees’ stress could manifest in official written communication. We identified negative emotions markers and analysed the relationships between the ticket registration frequency and negative emotion markers. Our interdisciplinary research confirmed that there is high and positive correlation between the stress measurement results based on the established psychometric survey and sentiment analysis results of help desk ticket data set. We conclude that the novel tool we proposed allows for continuous monitoring of DTS among employees in any organization, without psychometric surveys. It is an attractive alternative to lengthy questionnaires, as it makes better use of employees’ time while continuously monitoring stress levels to evaluate at any time if an intervention, such as training, tool upgrade or any other support is needed to safeguard employee’s job satisfaction and their well-being.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83704505","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}
{"title":"Medication Recommendation Based on a Knowledge-enhanced Pre-training Model","authors":"Mengzhen Wang, Jianhui Chen, Shaofu Lin","doi":"10.1145/3498851.3498968","DOIUrl":"https://doi.org/10.1145/3498851.3498968","url":null,"abstract":"More and more attention has been paid to electronic medical record (EMR)-based auxiliary diagnosis and treatment, in which medication recommendation is an important research direction. The existing medication recommendation models mainly depend on the data of patients, diagnosis and medications. However, the insufficient amount of clinical data with temporal dependencies becomes a major obstacle. This paper proposes a new knowledge-enhanced pre-training model for medication recommendation. On the one hand, the classification knowledge in diagnostic codes and drug codes is encoded by Graph Attention Network and fused into the clinical data for expanding the data content. On the other hand, a large number of single visit data of EMR are used to create the pre-trained visit model by a modified BERT for expanding the data scale. The experimental results on EMR data from more than 2,000 medical and health institutions in Hainan, China show that the fusion of classification knowledge and pre-training model can effectively improve the accuracy of medication recommendation.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"92 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73442611","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}
{"title":"Session details: Chapter 4: NLPOE2021: 14th Natural Language Processing and Ontology Engineering","authors":"","doi":"10.1145/3530277","DOIUrl":"https://doi.org/10.1145/3530277","url":null,"abstract":"","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"40 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76934738","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}
Kentaro Ueda, Kodai Sasaki, H. Suwa, Yuki Ogawa, Eiichi Umehara, Tatsuo Yamashita, K. Tsubouchi, K. Yasumoto
{"title":"Prediction of Nikkei VI increase for reducing investment risk using Yahoo! JAPAN stock BBS","authors":"Kentaro Ueda, Kodai Sasaki, H. Suwa, Yuki Ogawa, Eiichi Umehara, Tatsuo Yamashita, K. Tsubouchi, K. Yasumoto","doi":"10.1145/3498851.3498940","DOIUrl":"https://doi.org/10.1145/3498851.3498940","url":null,"abstract":"In stock investment, it is important to predict future market fluctuations in order to reduce risk. The Nikkei 225 Volatility Index (VI) is a measure of the expectations of the investors of the future of the Japanese market. A rise in this index indicates that investors are concerned about the future of the market, and predicting this rise may be used to reduce investment risk. Social media posts contain the opinions and feelings of the posters. In the present study, we proposed a means of predicting the increase in the Nikkei 225 VI by analyzing the social media of the largest stock trading website in Japan, ”Yahoo! Japan Stock Message Board,” and capturing changes in the topics of discussion. As a result of evaluation over a long validation period, we developed a prediction model with an F1-measure of 0.26.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"51 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78299186","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}
{"title":"Mobile Crowdsensing with Imagery Tasks","authors":"Justas Dautaras, M. Matskin","doi":"10.1145/3498851.3498929","DOIUrl":"https://doi.org/10.1145/3498851.3498929","url":null,"abstract":"The amount of gadgets connected to the internet has grown rapidly in the recent years. These human owned devices can potentially be used to gather sensor data without active involvement of their owners. One of the types of platforms that contribute to the utilisation of these devices are mobile crowdsensing systems. These systems can be used for different tasks including different types of community support. While these systems are quite widely used, yet little research has been done for integration of imagery data into them which require also human involvement. This paper considers a mobile crowdsensing system where gathering data from sensors is supported by crowdsourcing human intelligence for providing both textual and visual information. We also explore the best settings for such a system. Imagery processing is integrated into an already existing mobile crowdsensing platform CrowdS. The solution was evaluated both by a limited number of real life users and by conducting simulations. The simulations represent complex scenarios with multi-level variables. The results of simulation allow suggest an efficient configuration for the parameters and characteristics of the environment used in imagery integration.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74287594","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}
Tatiana Ermakova, Benjamin Fabian, David Alexander Fradin, Sebastian Gross
{"title":"A Framework for Internet Connectivity Risk Assessment Based on Graph Models","authors":"Tatiana Ermakova, Benjamin Fabian, David Alexander Fradin, Sebastian Gross","doi":"10.1145/3486622.3493980","DOIUrl":"https://doi.org/10.1145/3486622.3493980","url":null,"abstract":"Autonomous systems (AS) that relay Internet traffic are not equally well connected. The failure of just a tiny portion of them can render multiple sites inaccessible and disconnect multiple service providers from the global network, while targeted attacks can severely impact Internet connectivity. Modeling Internet topology and measuring Internet connectivity can help determine Internet vulnerabilities and improve Internet performance. With this in mind, we have redesigned and implemented a framework called CORIA that enables the analysis of Internet connectivity risks using large network graphs. The requirements we set for the design include technological extensibility, combination of different data sets, intuitive and customizable user interface, rich visual representation of results, and performance efficiency.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84577657","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}
{"title":"Evaluation index system and methodology for actively responding to ageing population","authors":"Si-bo Yang, Ai-hua Li, Guijun Li","doi":"10.1145/3498851.3499005","DOIUrl":"https://doi.org/10.1145/3498851.3499005","url":null,"abstract":"Ageing population is a challenge faced by the global community. According to international standards for measuring ageing society, China has entered the ageing society since 2000. Currently, actively responding to ageing population has become one of China's national strategies. Increasingly, actively responding to ageing population is gaining greater attention, but there lacks a comprehensive evaluation index system and model. Based on China's real situations, we scientifically and comprehensively construct an evaluation index system for actively responding to ageing population, using source statistical surveys, social tracking surveys and other multi-source heterogeneous data. Best-Worst Method (BWM) and K-means clustering algorithm are used here to evaluate ageing population measuring nationwide with a scientific and comprehensive index system. This paper also analyses and evaluates the measurement taken by 31 districts in China, thus carrying both theoretical and practical implications. With the emergence of big data for government administration, the rigor of the evaluation outcome will enhance.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82171096","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}
{"title":"SCAN:Syntactic Knowledge and Commonsense Knowledge Adapter Based Network for Aspect-level Sentiment Classification","authors":"Guojun Lu, Haibo Yu, Yun Xue, Zhixun Qiu, Weiyu Zhong","doi":"10.1145/3498851.3498985","DOIUrl":"https://doi.org/10.1145/3498851.3498985","url":null,"abstract":"Aspect-level sentiment classification is a most pronounced approach, which is defined as an automated technique to extract significant information from a large number of texts. However, current research still has limitations in ALSC tasks (e.g. accuracy of dependency parsing and overlook of commonsense knowledge). In this work, we propose a syntactic knowledge and commonsense knowledge adapter based network, which deals with the position information, syntactic structure and external knowledge, respectively. The performance of our model is evaluated on the three benchmark datasets. Experimental results demonstrate that our model is a best alternative in ALSC tasks compared with the state-of-the-art methods.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"33 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84669536","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}