The present paper describes briefly a project idea in progress about the evolvement of individuals' opinions, beliefs and perceptions on social networks (such as Facebook, Twitter, Instagram, youtube...) which is a thorny subject that has whetted nowadays the curiosity of a hulk of researchers from various disciplines. For this purpose, differently from a lot of works in the literature, we rely on logical knowledge representation tools in order to investigate the belief merging operation of Artificial Intelligence (AI). The major objective of this project is to provide efficient operator for merging heterogeneous, inconsistent and uncertain multiple sources information in the context of social networks taking into account the fact that opinion can be formed and developed through the concept of social influence with its two forms (informational social influence and normative social influence) and the concept of social trust. We intend thus through this research work presenting an adaptative version to our context of an approach [7] expressed thanks to Answer Set Programming (ASP) paradigm with stable model semantics. It is worth to say that our approach profits from the impressive volume data produced by users in social networks about a particular topic by learning from opinions, beliefs and perceptions that their freinds/neighbors share and therefore allows to use this kind of data to extract initial opinions, and to validate the proposed opinions merging process allowing even the prediction of users' behaviors.
{"title":"Answer set programming encoding users opinions merging in social networks","authors":"R. Ktari, Salma Jamoussi","doi":"10.1145/3428757.3429150","DOIUrl":"https://doi.org/10.1145/3428757.3429150","url":null,"abstract":"The present paper describes briefly a project idea in progress about the evolvement of individuals' opinions, beliefs and perceptions on social networks (such as Facebook, Twitter, Instagram, youtube...) which is a thorny subject that has whetted nowadays the curiosity of a hulk of researchers from various disciplines. For this purpose, differently from a lot of works in the literature, we rely on logical knowledge representation tools in order to investigate the belief merging operation of Artificial Intelligence (AI). The major objective of this project is to provide efficient operator for merging heterogeneous, inconsistent and uncertain multiple sources information in the context of social networks taking into account the fact that opinion can be formed and developed through the concept of social influence with its two forms (informational social influence and normative social influence) and the concept of social trust. We intend thus through this research work presenting an adaptative version to our context of an approach [7] expressed thanks to Answer Set Programming (ASP) paradigm with stable model semantics. It is worth to say that our approach profits from the impressive volume data produced by users in social networks about a particular topic by learning from opinions, beliefs and perceptions that their freinds/neighbors share and therefore allows to use this kind of data to extract initial opinions, and to validate the proposed opinions merging process allowing even the prediction of users' behaviors.","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"331 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122743851","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}
There is a growing need to anonymize data as new businesses are increasingly utilizing vast amount of unstructured text. Also, unstructured text have a risk of personal location estimation by considering location information. Nevertheless, existing generalizations do not take into location information and therefore cannot robustly handle this attack. In this study, we proposed anonymizing location information in unstructured text using knowledge graph newly constructed from an actual geographic information system. Our method has the advantages of anonymization, taking into account actual geographic information, handling abbreviations and spelling inconsistencies, and allowing for dynamic graph updates. The results of the evaluation experiments show that anonymization is more robust than existing methods against location estimation attacks without compromising its usefulness as a dataset. Also, we found that the names of organizations and places with a high probability of occurrence in unstructured text are more likely to lead to personal identification.
{"title":"Anonymizing Location Information in Unstructured Text Using Knowledge Graph","authors":"Taisho Sasada, Yuzo Taenaka, Y. Kadobayashi","doi":"10.1145/3428757.3429195","DOIUrl":"https://doi.org/10.1145/3428757.3429195","url":null,"abstract":"There is a growing need to anonymize data as new businesses are increasingly utilizing vast amount of unstructured text. Also, unstructured text have a risk of personal location estimation by considering location information. Nevertheless, existing generalizations do not take into location information and therefore cannot robustly handle this attack. In this study, we proposed anonymizing location information in unstructured text using knowledge graph newly constructed from an actual geographic information system. Our method has the advantages of anonymization, taking into account actual geographic information, handling abbreviations and spelling inconsistencies, and allowing for dynamic graph updates. The results of the evaluation experiments show that anonymization is more robust than existing methods against location estimation attacks without compromising its usefulness as a dataset. Also, we found that the names of organizations and places with a high probability of occurrence in unstructured text are more likely to lead to personal identification.","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133939641","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}
R. Philipp, Andreas Mladenow, C. Strauss, Alexander Völz
This study aims to evaluate the current state of research with regards to Machine Learning as a Service (MLaaS) and to identify challenges and research fields of this novel topic. First, a literature review on a basket of eight leading journals was performed. We motivate this study by identifying a lack of studies in the field of MLaaS. The structured literature review was further extended to established scientific databases relevant in this field. We found 30 contributions on MLaaS. As a result of the analysis we grouped them into four key concepts: Platform, Applications; Performance Enhancements and Challenges. Three of the derived concepts are discussed in detail to identify future research areas and to reveal challenges in research as well as in applications.
{"title":"Machine Learning as a Service: Challenges in Research and Applications","authors":"R. Philipp, Andreas Mladenow, C. Strauss, Alexander Völz","doi":"10.1145/3428757.3429152","DOIUrl":"https://doi.org/10.1145/3428757.3429152","url":null,"abstract":"This study aims to evaluate the current state of research with regards to Machine Learning as a Service (MLaaS) and to identify challenges and research fields of this novel topic. First, a literature review on a basket of eight leading journals was performed. We motivate this study by identifying a lack of studies in the field of MLaaS. The structured literature review was further extended to established scientific databases relevant in this field. We found 30 contributions on MLaaS. As a result of the analysis we grouped them into four key concepts: Platform, Applications; Performance Enhancements and Challenges. Three of the derived concepts are discussed in detail to identify future research areas and to reveal challenges in research as well as in applications.","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115356512","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}
With the prevalence and rapid proliferation of SNS, dissemination of false information has become a big problem. In this paper, targeting Twitter, we propose a two-step approach for early detection of false information based on machine learning, which considers the event occurrence scale and the time series of tweets that compose the event. In Step 1, in the early stage of an event, whether it is false or true is decided if the prediction probability is high enough. In Step 2, the events whose authenticity cannot be determined in Step 1 are targeted for tracking, and their authenticity is ascertained as the tweets related to the events increase gradually. The experimental results comparing five machine learning models show that SVM is the optimal model for both steps and that our approach can achieve early detection of false information.
{"title":"Early Automatic Detection of False Information in Twitter Event Considering Occurrence Scale and Time Series","authors":"Jianwei Zhang, Jinto Yamanaka, Lin Li","doi":"10.1145/3428757.3429115","DOIUrl":"https://doi.org/10.1145/3428757.3429115","url":null,"abstract":"With the prevalence and rapid proliferation of SNS, dissemination of false information has become a big problem. In this paper, targeting Twitter, we propose a two-step approach for early detection of false information based on machine learning, which considers the event occurrence scale and the time series of tweets that compose the event. In Step 1, in the early stage of an event, whether it is false or true is decided if the prediction probability is high enough. In Step 2, the events whose authenticity cannot be determined in Step 1 are targeted for tracking, and their authenticity is ascertained as the tweets related to the events increase gradually. The experimental results comparing five machine learning models show that SVM is the optimal model for both steps and that our approach can achieve early detection of false information.","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117200800","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}
N. Khan, T. Mahmud, M. Islam, Sumaiya Nuha Mustafina
Cesarean section around the world is increasing at an alarming rate. Cesarean section, on one hand, may introduce different short-term and long-term complications for mother; on another hand it may be a life-saving procedure for both mother and child, depending on childbirth complications. The purpose of this research is to predict whether or not the cesarean section is necessary with the help of data mining and consequently, increasing the safety of the mother and newborn during and after childbirth by avoiding unnecessary cesarean section. To attain the objective three different ensemble prediction models based on- XGBoost, AdaBoost and Catboost were developed. As an outcome XGBoost showed the highest accuracy-88.91% while AdaBoost showed 88.69% accuracy and Catboost showed 87.66% accuracy. This research also revealed that amniotic liquid, medical indication, fetal intrapartum ph, number of previous cesareans, pre-induction are the most influential features for predicting the target outcome accurately.
{"title":"Prediction of Cesarean Childbirth using Ensemble Machine Learning Methods","authors":"N. Khan, T. Mahmud, M. Islam, Sumaiya Nuha Mustafina","doi":"10.1145/3428757.3429138","DOIUrl":"https://doi.org/10.1145/3428757.3429138","url":null,"abstract":"Cesarean section around the world is increasing at an alarming rate. Cesarean section, on one hand, may introduce different short-term and long-term complications for mother; on another hand it may be a life-saving procedure for both mother and child, depending on childbirth complications. The purpose of this research is to predict whether or not the cesarean section is necessary with the help of data mining and consequently, increasing the safety of the mother and newborn during and after childbirth by avoiding unnecessary cesarean section. To attain the objective three different ensemble prediction models based on- XGBoost, AdaBoost and Catboost were developed. As an outcome XGBoost showed the highest accuracy-88.91% while AdaBoost showed 88.69% accuracy and Catboost showed 87.66% accuracy. This research also revealed that amniotic liquid, medical indication, fetal intrapartum ph, number of previous cesareans, pre-induction are the most influential features for predicting the target outcome accurately.","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115120120","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}
Teresa Alcamo, A. Cuzzocrea, Giosuè Lo Bosco, G. Pilato, Daniele Schicchi
In this paper, we tackle the problem of the irony and sarcasm detection for the Italian language to contribute to the enrichment of the sentiment analysis field. We analyze and compare five deep-learning systems. Results show the high suitability of such systems to face the problem by achieving 93% of F1-Score in the best case. Furthermore, we briefly analyze the model architectures in order to choose the best compromise between performances and complexity.
{"title":"Analysis and Comparison of Deep Learning Networks for Supporting Sentiment Mining in Text Corpora","authors":"Teresa Alcamo, A. Cuzzocrea, Giosuè Lo Bosco, G. Pilato, Daniele Schicchi","doi":"10.1145/3428757.3429144","DOIUrl":"https://doi.org/10.1145/3428757.3429144","url":null,"abstract":"In this paper, we tackle the problem of the irony and sarcasm detection for the Italian language to contribute to the enrichment of the sentiment analysis field. We analyze and compare five deep-learning systems. Results show the high suitability of such systems to face the problem by achieving 93% of F1-Score in the best case. Furthermore, we briefly analyze the model architectures in order to choose the best compromise between performances and complexity.","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123670560","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}
Energy demand has increased over the last few years, it is increasing faster than new technologies are being developed and faster than new energy sources can be found. The study explored the factors affecting the adoption smart energy at universities. The study adopted the technological, organisational and environmental factors (TOE) Framework to explore factors affecting smart energy adoption. The study used systematic literature review of articles published on smart energy. The quantitative content analysis was used to analyse the data from to review published articles smart energy adoption. The study results suggest that environmental factors (sustainability, global warming) are more important smart energy adoption factors than technological and organisational factors. The cost of technology is also perceived as an important factor. The study contributes to literature on the factors affecting smart energy at universities
{"title":"Factors Affecting the Adoption of Smart Energy at Universities","authors":"J. C. Nel, Osden Jokonya","doi":"10.1145/3428757.3429099","DOIUrl":"https://doi.org/10.1145/3428757.3429099","url":null,"abstract":"Energy demand has increased over the last few years, it is increasing faster than new technologies are being developed and faster than new energy sources can be found. The study explored the factors affecting the adoption smart energy at universities. The study adopted the technological, organisational and environmental factors (TOE) Framework to explore factors affecting smart energy adoption. The study used systematic literature review of articles published on smart energy. The quantitative content analysis was used to analyse the data from to review published articles smart energy adoption. The study results suggest that environmental factors (sustainability, global warming) are more important smart energy adoption factors than technological and organisational factors. The cost of technology is also perceived as an important factor. The study contributes to literature on the factors affecting smart energy at universities","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129254293","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}
Data integration is the process of selecting, preprocessing, and transforming data from heterogeneous sources in data-driven projects. This process also requires the most time, effort, resources. Data integration is such an involved process due to the many informed decisions one has to make. These decisions are influenced by the complex context of a data-driven project. We argue that using said context could facilitate the decision-making processes and even automate some integration steps. However, the problem we identify in this paper is that the context of a data-driven project is tacit and, therefore, not easily accessible by humans and certainly not by software agents. From the SotA, however, we observe that current models represent the context in crude and simplistic terms. These context models are furthermore built for specific tasks or application domains such as query optimization or a smart home. The current state of affairs is thus is not fit for intelligent data integration. Next to identifying the problem, we postulate that solving this problem requires two steps: formalizing context and using that context for building context-aware agents. We illustrate this notion of "context-aware data integration" with preliminary results obtained with a use case in the domain of GDPR, more specifically the generation of datasets that takes into account informed consent.
{"title":"Introducing Context and Context-awareness in Data Integration: Identifying the Problem and a Preliminary Case Study on Informed Consent","authors":"C. Debruyne","doi":"10.1145/3428757.3429116","DOIUrl":"https://doi.org/10.1145/3428757.3429116","url":null,"abstract":"Data integration is the process of selecting, preprocessing, and transforming data from heterogeneous sources in data-driven projects. This process also requires the most time, effort, resources. Data integration is such an involved process due to the many informed decisions one has to make. These decisions are influenced by the complex context of a data-driven project. We argue that using said context could facilitate the decision-making processes and even automate some integration steps. However, the problem we identify in this paper is that the context of a data-driven project is tacit and, therefore, not easily accessible by humans and certainly not by software agents. From the SotA, however, we observe that current models represent the context in crude and simplistic terms. These context models are furthermore built for specific tasks or application domains such as query optimization or a smart home. The current state of affairs is thus is not fit for intelligent data integration. Next to identifying the problem, we postulate that solving this problem requires two steps: formalizing context and using that context for building context-aware agents. We illustrate this notion of \"context-aware data integration\" with preliminary results obtained with a use case in the domain of GDPR, more specifically the generation of datasets that takes into account informed consent.","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130902980","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}
Andreas Müller, Stefan Mitsch, W. Retschitzegger, W. Schwinger
While formal verification techniques are inevitable to ensure safety of critical cyber-phyical systems (CPS), engineering techniques to support the design and analysis of such CPS are still in their infancy. Therefore, we take a first step towards the provision of appropriate engineering techniques for CPS verification, by providing an extensive evaluation of the current state of the art, identifying challenges not yet tackled by existing approaches and by proposing a research roadmap intended to pave the way towards a fully supported engineering process for CPS verification models.
{"title":"Towards CPS Verification Engineering","authors":"Andreas Müller, Stefan Mitsch, W. Retschitzegger, W. Schwinger","doi":"10.1145/3428757.3429146","DOIUrl":"https://doi.org/10.1145/3428757.3429146","url":null,"abstract":"While formal verification techniques are inevitable to ensure safety of critical cyber-phyical systems (CPS), engineering techniques to support the design and analysis of such CPS are still in their infancy. Therefore, we take a first step towards the provision of appropriate engineering techniques for CPS verification, by providing an extensive evaluation of the current state of the art, identifying challenges not yet tackled by existing approaches and by proposing a research roadmap intended to pave the way towards a fully supported engineering process for CPS verification models.","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131487644","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}
Airbnb is a peer-to-peer accommodation website in the sharing economy. Past studies have examined the factors associated with Airbnb utilization from various platforms, but not exclusively from Twitter. A total of 21,097 tweets was collected in a period of two months, and the tweets were qualitatively analyzed with the help of text analysis tools to verify the discourse of discussion. Literature was reviewed for common factors attracting clients to an Airbnb accommodation. Factors were then qualitatively analyzed and compiled using Wmatrix, and the themes that emerged were: Price and status, social interaction and communication, location, reputation, amenities and a pet-friendly environment. This result provides a deeper insight to Airbnb hosts to strategize and add value to their current market situations.
{"title":"Viewing Airbnb from Twitter: factors associated with users' utilization","authors":"P. Teh, Y. Low, Pei Boon Ooi","doi":"10.1145/3428757.3429112","DOIUrl":"https://doi.org/10.1145/3428757.3429112","url":null,"abstract":"Airbnb is a peer-to-peer accommodation website in the sharing economy. Past studies have examined the factors associated with Airbnb utilization from various platforms, but not exclusively from Twitter. A total of 21,097 tweets was collected in a period of two months, and the tweets were qualitatively analyzed with the help of text analysis tools to verify the discourse of discussion. Literature was reviewed for common factors attracting clients to an Airbnb accommodation. Factors were then qualitatively analyzed and compiled using Wmatrix, and the themes that emerged were: Price and status, social interaction and communication, location, reputation, amenities and a pet-friendly environment. This result provides a deeper insight to Airbnb hosts to strategize and add value to their current market situations.","PeriodicalId":212557,"journal":{"name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130151672","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：