Pub Date : 2024-05-24DOI: 10.1007/s10115-024-02111-9
Kiattikun Chobtham, Anthony C. Constantinou
One of the challenges practitioners face when applying structure learning algorithms to their data involves determining a set of hyperparameters; otherwise, a set of hyperparameter defaults is assumed. The optimal hyperparameter configuration often depends on multiple factors, including the size and density of the usually unknown underlying true graph, the sample size of the input data, and the structure learning algorithm. We propose a novel hyperparameter tuning method, called the Out-of-sample Tuning for Structure Learning (OTSL), that employs out-of-sample and resampling strategies to estimate the optimal hyperparameter configuration for structure learning, given the input dataset and structure learning algorithm. Synthetic experiments show that employing OTSL to tune the hyperparameters of hybrid and score-based structure learning algorithms leads to improvements in graphical accuracy compared to the state-of-the-art. We also illustrate the applicability of this approach to real datasets from different disciplines.
{"title":"Tuning structure learning algorithms with out-of-sample and resampling strategies","authors":"Kiattikun Chobtham, Anthony C. Constantinou","doi":"10.1007/s10115-024-02111-9","DOIUrl":"https://doi.org/10.1007/s10115-024-02111-9","url":null,"abstract":"<p>One of the challenges practitioners face when applying structure learning algorithms to their data involves determining a set of hyperparameters; otherwise, a set of hyperparameter defaults is assumed. The optimal hyperparameter configuration often depends on multiple factors, including the size and density of the usually unknown underlying true graph, the sample size of the input data, and the structure learning algorithm. We propose a novel hyperparameter tuning method, called the Out-of-sample Tuning for Structure Learning (OTSL), that employs out-of-sample and resampling strategies to estimate the optimal hyperparameter configuration for structure learning, given the input dataset and structure learning algorithm. Synthetic experiments show that employing OTSL to tune the hyperparameters of hybrid and score-based structure learning algorithms leads to improvements in graphical accuracy compared to the state-of-the-art. We also illustrate the applicability of this approach to real datasets from different disciplines.</p>","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141148035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-23DOI: 10.1007/s10115-024-02126-2
Bidyapati Thiyam, Shouvik Dey
{"title":"CIIR: an approach to handle class imbalance using a novel feature selection technique","authors":"Bidyapati Thiyam, Shouvik Dey","doi":"10.1007/s10115-024-02126-2","DOIUrl":"https://doi.org/10.1007/s10115-024-02126-2","url":null,"abstract":"","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141105908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-23DOI: 10.1007/s10115-024-02129-z
S. R. Lenka, S. Bisoy, R. Priyadarshini
{"title":"Multiple optimized ensemble learning for high-dimensional imbalanced credit scoring datasets","authors":"S. R. Lenka, S. Bisoy, R. Priyadarshini","doi":"10.1007/s10115-024-02129-z","DOIUrl":"https://doi.org/10.1007/s10115-024-02129-z","url":null,"abstract":"","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141106523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-23DOI: 10.1007/s10115-023-02039-6
I. Aldalur, Alain Perez, F. Larrinaga, Miren Illarramendi
{"title":"A visual programming tool for mobile web augmentation","authors":"I. Aldalur, Alain Perez, F. Larrinaga, Miren Illarramendi","doi":"10.1007/s10115-023-02039-6","DOIUrl":"https://doi.org/10.1007/s10115-023-02039-6","url":null,"abstract":"","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141106410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-23DOI: 10.1007/s10115-024-02124-4
Ting-Ting Wu, Xiao Ding, Li Du, Bing Qin, Ting Liu
{"title":"Reasoning subevent relation over heterogeneous event graph","authors":"Ting-Ting Wu, Xiao Ding, Li Du, Bing Qin, Ting Liu","doi":"10.1007/s10115-024-02124-4","DOIUrl":"https://doi.org/10.1007/s10115-024-02124-4","url":null,"abstract":"","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141105173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-18DOI: 10.1007/s10115-024-02128-0
Diego M. Jiménez-Bravo, Javier Bajo, Jacinto González-Pachón, Juan F. De Paz
Road safety remains a critical issue in contemporary society, where the sudden deterioration of road conditions due to weather-related natural phenomena poses significant risks. These abrupt changes can lead to severe safety hazards on the roads, making real-time monitoring and control essential for maintaining road safety. In this context, technological advancements, especially in sensor networks and intelligent systems, play a fundamental role in efficiently managing these challenges. This study introduces an innovative approach that leverages a sophisticated sensor platform coupled with a multi-agent system. This integration facilitates the collection, processing, and analysis of data to preemptively determine the appropriate chemical treatments for roads during severe winter conditions. By employing advanced data analysis and machine learning techniques within a multi-agent framework, the system can predict and respond to adverse weather effects swiftly and with a high degree of accuracy. The proposed system has undergone rigorous testing in a real-world environment, which has verified its operational effectiveness. The results from the deployment of the multi-agent architecture and its predictive capabilities are encouraging, suggesting that this approach could significantly enhance road safety in extreme weather conditions. Furthermore, the proposed architecture allows the system to evolve and scale over time. This paper details the design and implementation of the system, discusses the results of its field tests, and explores potential improvements.
{"title":"Multi-agent system architecture for winter road maintenance: a real Spanish case study","authors":"Diego M. Jiménez-Bravo, Javier Bajo, Jacinto González-Pachón, Juan F. De Paz","doi":"10.1007/s10115-024-02128-0","DOIUrl":"https://doi.org/10.1007/s10115-024-02128-0","url":null,"abstract":"<p>Road safety remains a critical issue in contemporary society, where the sudden deterioration of road conditions due to weather-related natural phenomena poses significant risks. These abrupt changes can lead to severe safety hazards on the roads, making real-time monitoring and control essential for maintaining road safety. In this context, technological advancements, especially in sensor networks and intelligent systems, play a fundamental role in efficiently managing these challenges. This study introduces an innovative approach that leverages a sophisticated sensor platform coupled with a multi-agent system. This integration facilitates the collection, processing, and analysis of data to preemptively determine the appropriate chemical treatments for roads during severe winter conditions. By employing advanced data analysis and machine learning techniques within a multi-agent framework, the system can predict and respond to adverse weather effects swiftly and with a high degree of accuracy. The proposed system has undergone rigorous testing in a real-world environment, which has verified its operational effectiveness. The results from the deployment of the multi-agent architecture and its predictive capabilities are encouraging, suggesting that this approach could significantly enhance road safety in extreme weather conditions. Furthermore, the proposed architecture allows the system to evolve and scale over time. This paper details the design and implementation of the system, discusses the results of its field tests, and explores potential improvements.</p>","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141058681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-18DOI: 10.1007/s10115-024-02130-6
Fan Zhang, Yaoyao Zhou, Pengfei Sun, Yi Xu, Wanjiang Han, Hongben Huang, Jinpeng Chen
To address the problem of sparse data and cold-start when facing new users and items in the single-domain recommendation, cross-domain recommendation has gradually become a hot topic in the recommendation system. This method enhances target domain recommendation performance by incorporating relevant information from an auxiliary domain. A critical aspect of cross-domain recommendation is the effective transfer of user preferences from the source to the target domain. This paper proposes a novel cross-domain recommendation framework, namely the Cross-domain Recommendation based on Aspect-level Sentiment extraction (CRAS). CRAS leverages user and item review texts in cross-domain recommendations to extract detailed user preferences. Specifically, the Biterm Topic Model (BTM) is utilized for the precise extraction of ’aspects’ from users and items, focusing on identifying characteristics that align with user interests and the positive attributes of items. These ’aspects’ represent distinct, influential features of the items. For example, a good service attitude can be regarded as a good aspect of a restaurant. Furthermore, this study employs an improved Cycle-Consistent Generative Adversarial Networks (CycleGAN), efficiently mapping user preferences from one domain to another, thereby enhancing the accuracy and personalization of the recommendations. Lastly, this paper compares the CRAS model with a series of state-of-the-art baseline methods in the Amazon review dataset, and experiment results show that the proposed model outperforms the baseline methods.
{"title":"CRAS: cross-domain recommendation via aspect-level sentiment extraction","authors":"Fan Zhang, Yaoyao Zhou, Pengfei Sun, Yi Xu, Wanjiang Han, Hongben Huang, Jinpeng Chen","doi":"10.1007/s10115-024-02130-6","DOIUrl":"https://doi.org/10.1007/s10115-024-02130-6","url":null,"abstract":"<p>To address the problem of sparse data and cold-start when facing new users and items in the single-domain recommendation, cross-domain recommendation has gradually become a hot topic in the recommendation system. This method enhances target domain recommendation performance by incorporating relevant information from an auxiliary domain. A critical aspect of cross-domain recommendation is the effective transfer of user preferences from the source to the target domain. This paper proposes a novel cross-domain recommendation framework, namely the Cross-domain Recommendation based on Aspect-level Sentiment extraction (CRAS). CRAS leverages user and item review texts in cross-domain recommendations to extract detailed user preferences. Specifically, the Biterm Topic Model (BTM) is utilized for the precise extraction of ’aspects’ from users and items, focusing on identifying characteristics that align with user interests and the positive attributes of items. These ’aspects’ represent distinct, influential features of the items. For example, a good service attitude can be regarded as a good aspect of a restaurant. Furthermore, this study employs an improved Cycle-Consistent Generative Adversarial Networks (CycleGAN), efficiently mapping user preferences from one domain to another, thereby enhancing the accuracy and personalization of the recommendations. Lastly, this paper compares the CRAS model with a series of state-of-the-art baseline methods in the Amazon review dataset, and experiment results show that the proposed model outperforms the baseline methods.\u0000</p>","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141058597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-17DOI: 10.1007/s10115-024-02118-2
Ramadhani Ally Duma, Zhendong Niu, Ally S. Nyamawe, Jude Tchaye-Kondi, Nuru Jingili, Abdulganiyu Abdu Yusuf, Augustino Faustino Deve
Recently, the impact of product or service reviews on customers' purchasing decisions has become increasingly significant in online businesses. Consequently, manipulating reviews for fame or profit has become prevalent, with some businesses resorting to paying fake reviewers to post spam reviews. Given the importance of reviews in decision-making, detecting fake reviews is crucial to ensure fair competition and sustainable e-business practices. Although significant efforts have been made in the last decade to distinguish credible reviews from fake ones, it remains challenging. Our literature review has identified several gaps in the existing research: (1) most fake review detection techniques have been proposed for high-resource languages such as English and Chinese, and few studies have investigated low-resource and multilingual fake review detection, (2) there is a lack of research on deceptive review detection for reviews based on language code-switching (code-mix), (3) current multi-feature integration techniques extract review representations independently, ignoring correlations between them, and (4) there is a lack of a consolidated model that can mutually learn from review emotion, coarse-grained (overall rating), and fine-grained (aspect ratings) features to supplement the problem of sentiment and overall rating inconsistency. In light of these gaps, this study aims to provide an in-depth literature analysis describing strengths and weaknesses, open issues, and future research directions.
{"title":"Fake review detection techniques, issues, and future research directions: a literature review","authors":"Ramadhani Ally Duma, Zhendong Niu, Ally S. Nyamawe, Jude Tchaye-Kondi, Nuru Jingili, Abdulganiyu Abdu Yusuf, Augustino Faustino Deve","doi":"10.1007/s10115-024-02118-2","DOIUrl":"https://doi.org/10.1007/s10115-024-02118-2","url":null,"abstract":"<p>Recently, the impact of product or service reviews on customers' purchasing decisions has become increasingly significant in online businesses. Consequently, manipulating reviews for fame or profit has become prevalent, with some businesses resorting to paying fake reviewers to post spam reviews. Given the importance of reviews in decision-making, detecting fake reviews is crucial to ensure fair competition and sustainable e-business practices. Although significant efforts have been made in the last decade to distinguish credible reviews from fake ones, it remains challenging. Our literature review has identified several gaps in the existing research: (1) most fake review detection techniques have been proposed for high-resource languages such as English and Chinese, and few studies have investigated low-resource and multilingual fake review detection, (2) there is a lack of research on deceptive review detection for reviews based on language code-switching (code-mix), (3) current multi-feature integration techniques extract review representations independently, ignoring correlations between them, and (4) there is a lack of a consolidated model that can mutually learn from review emotion, coarse-grained (overall rating), and fine-grained (aspect ratings) features to supplement the problem of sentiment and overall rating inconsistency. In light of these gaps, this study aims to provide an in-depth literature analysis describing strengths and weaknesses, open issues, and future research directions.</p>","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141058605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-16DOI: 10.1007/s10115-024-02106-6
K. P. Muhammed Niyas, Thiyagarajan Paramasivan
{"title":"Improving Alzheimer’s classification using a modified Borda count voting method on dynamic ensemble classifiers","authors":"K. P. Muhammed Niyas, Thiyagarajan Paramasivan","doi":"10.1007/s10115-024-02106-6","DOIUrl":"https://doi.org/10.1007/s10115-024-02106-6","url":null,"abstract":"","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140970130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-16DOI: 10.1007/s10115-024-02127-1
Diyawu Mumin, Lei-Lei Shi, Lu Liu, Zi-xuan Han, Liang Jiang, Yan Wu
{"title":"A new neighbourhood-based diffusion algorithm for personalized recommendation","authors":"Diyawu Mumin, Lei-Lei Shi, Lu Liu, Zi-xuan Han, Liang Jiang, Yan Wu","doi":"10.1007/s10115-024-02127-1","DOIUrl":"https://doi.org/10.1007/s10115-024-02127-1","url":null,"abstract":"","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140968002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}