Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology最新文献

{"title":"Differentially Private Multi-Agent Constraint Optimization","authors":"Sankarshan Damle, Aleksei Triastcyn, B. Faltings, Sujit Gujar","doi":"10.1145/3486622.3493929","DOIUrl":"https://doi.org/10.1145/3486622.3493929","url":null,"abstract":"Several optimization scenarios involve multiple agents that desire to protect the privacy of their preferences. There are distributed algorithms for constraint optimization that provide improved privacy protection through secure multiparty computation. However, it comes at the expense of high computational complexity and does not constitute a rigorous privacy guarantee for optimization outcomes, as the result of the computation itself may compromise agents’ preferences. In this work, we show how to achieve privacy, specifically differential privacy, through the randomization of the solving process. In particular, we present P-Gibbs, which adapts the SD-Gibbs algorithm to obtain differential privacy guarantees with much higher computational efficiency. Experiments on graph coloring and meeting scheduling show the algorithm’s privacy-performance trade-off for varying privacy budgets, and the SD-Gibbs algorithm.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"101 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83618635","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":"Multi-user Online Three-Dimensional Marine Oil Spill Crisis Response System","authors":"Bingchan Li, Hongtao Ma, Bo Mao","doi":"10.1145/3498851.3498924","DOIUrl":"https://doi.org/10.1145/3498851.3498924","url":null,"abstract":"Based on analyzing of current situation and existing problems of marine oil spill emergency drill teaching in maritime colleges, the significance of online teaching and 3D simulation is expounded. In this paper, an online 3D marine oil spill emergency drill system was is proposed, which consists of five functional modules: oil spill emergency resource editor module, accident scene editing module, oil spill accident handling deduction module, evaluation and evaluation module and drill module. The scheme design and architecture of the online teaching system of 3D simulation are given, and the functional simulation is realized. The results show that the system can enable students to carry out online exercises and give instant feedback, support the sharing of maps of exercises between different schools, and support students to collaborate remotely via the Internet.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86272438","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":"Home Appliance Review Analysis Via Adversarial Reptile","authors":"Tai-Jung Kan, Chia-Hui Chang","doi":"10.1145/3486622.3493958","DOIUrl":"https://doi.org/10.1145/3486622.3493958","url":null,"abstract":"Studying discussion of products on social media can help manufacturers improve their products. Opinions provided through online reviews can immediately reflect whether the product is accepted by people, and which aspects of the product are most discussed. In this article, we divide the analysis of home appliances into three tasks, including named entity recognition (NER), aspect category extraction (ACE), and aspect category sentiment classification (ACSC). To improve the performance of ACSC, we combine the Reptile algorithm in meta learning with the concept of domain adversarial training to form the concept of the Adversarial Reptile algorithm. We found that the macro-F1 is improved from 68.6% (BERT fine-tuned model) to 70.3% (p-value 0.04).","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"60 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77215263","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":"Climbing Route Difficulty Grade Prediction and Explanation","authors":"Marina Andric, I. Ivanova, Francesco Ricci","doi":"10.1145/3486622.3493932","DOIUrl":"https://doi.org/10.1145/3486622.3493932","url":null,"abstract":"This article focuses on sport climbing and on the design of innovative tools for supporting climbers to browse and search routes to climb. The difficulty of a route, its grade, is normally assessed by expert climbers, named route setters. A regular climber, after trying a route, may perceive it more or less difficult than the route setter. It is important to estimate this climber’s perceived difficulty of the routes in order to suggest the routes that have a target perceived difficulty as expected by the climber. We develop a knowledge-based approach that uses domain-specific features to train a predictive model. Additionally, the problem is modeled as a rating prediction task in a recommender system, using a matrix factorization approach with a custom normalization solution. The knowledge-based approach enables us to develop a grade prediction explanation functionality. In off-line experiments, we demonstrate improvements over a baseline. Moreover, we show how the proposed techniques can be exploited in an app developed by a major company offering information services to the sport climbing market.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85658873","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":"Medical Inter-Specialty Referral Networks","authors":"Tatiana Ermakova, Benjamin Fabian, M. Erhart, T. Czihal, D. Stillfried","doi":"10.1145/3498851.3498930","DOIUrl":"https://doi.org/10.1145/3498851.3498930","url":null,"abstract":"Motivated by their increasing popularity and usefulness in the English-speaking world, we model and analyze patient referral networks for medical specialties based on Germany-wide claims data from the fourth quarter of 2015. Based on the average values of local graph measures, different groups of medical specialties could be distinguished. Family physicians have almost perfect average out-degree and closeness centrality. Based on the principal components applied to local graph measures, four clusters of local medical specialties could be identified, that are characteristic for (1) orthopedists, surgeons, otolaryngologists, dermatologists and internists; (2) non-medical psychotherapists, pediatricians, gynecologists, and ophthalmologists; (3) only family physicians in Bremen and internists in Hamburg and Saarland; (4) the remaining family physicians. This study can serve as a basis for further network simulations and monitoring to achieve the desired health care outcomes, optimal resource allocation and protection against infections.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"53 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73569279","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":"Redistribution in Public Project Problems via Neural Networks","authors":"Guanhua Wang, Wuli Zuo, M. Guo","doi":"10.1145/3486622.3493922","DOIUrl":"https://doi.org/10.1145/3486622.3493922","url":null,"abstract":"Many important problems in multiagent systems involve resource allocations. Self-interested agents may lie about their valuations if doing so increases their own utilities. Therefore, it is necessary to design mechanisms (collective decision-making rules) with desired properties and objectives. The VCG redistribution mechanisms are efficient (the agents who value the resources the most will be allocated), strategy-proof (the agents have no incentives to lie about their valuations), and weakly budget-balanced (no deficits). We focus on the VCG redistribution mechanisms for the classic public project problem, where a group of agents needs to decide whether or not to build a non-excludable public project. We design mechanisms via neural networks with two welfare-maximizing objectives: optimal in the worst case and optimal in expectation. Previous studies showed two worst-case optimal mechanisms for 3 agents, but worst-case optimal mechanisms have not been identified for more than 3 agents. For maximizing expected welfare, there are no existing results. We use neural networks to design VCG redistribution mechanisms. Neural networks have been used to design the redistribution mechanisms for multi-unit auctions with unit demand. We show that for the public project problem, the previously proposed neural networks, which led to optimal/near-optimal mechanisms for multi-unit auctions with unit demand, perform abysmally for the public project problem. We significantly improve the existing networks on multiple fronts: We conduct a GAN network to generate worst-case type profiles and feed prior distribution into loss function to provide quality gradients for the optimal-in-expectation objective. We adopt dimension reduction to handle a larger number of agents and we adopt supervised learning into the best manual mechanism as initialization, then leave it into unsupervised learning. For the worst case, we get better results than the existing manual mechanisms, and for the optimal-in-expectation objective, our mechanisms’ performances are close to the theoretical optimal performance.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85026272","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":"Does environmental awareness play a role in EV adoption? A value-based adoption model analysis with SEM-ANN approach","authors":"Sohaib Mustafa, Wen Zhang, Rui Li","doi":"10.1145/3498851.3498992","DOIUrl":"https://doi.org/10.1145/3498851.3498992","url":null,"abstract":"Abstract. Global warming is a serious threat to humanity, and one of the main reasons is that the transport sector contributes to CO2 emissions. The auto industry's Introduction of electric-powered vehicles (EVs) is widely viewed as the primary solution. Although electric vehicles (EVs) have numerous benefits, acceptance rates vary widely from country to country, and the promised reductions in energy shortages and emissions have not materialized. We used the Value-based technology adoption model and added Environmental awareness (EA) as a new factor in this model to assess the role of EA in EV adoption intentions. Because of the complexity in consumer adoption decisions and nonlinearity in the dataset, we proposed the SEM-ANN mixed-method approach to address these issues. We gathered responses from 751 EV users in China and used the SEM-ANN dual-stage mix model to evaluate presented hypotheses and prioritize factors by relevance. According to the study's findings, although EA is a major predictor of EV adoption, it is not the most important. According to the study's findings, perceptions of the benefits and sacrifices associated with EV adoption have a considerable influence on the perceived value of EV, so this worth drives adoption intentions. Government and the electric car manufacturing business stand to gain much from this research, both theoretically and practically.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"83 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88393090","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":"Assessing the use of attention weights to interpret BERT-based stance classification","authors":"Carlos Abel Córdova Sáenz, Karin Becker","doi":"10.1145/3486622.3493966","DOIUrl":"https://doi.org/10.1145/3486622.3493966","url":null,"abstract":"BERT models are currently state-of-the-art solutions for various tasks, including stance classification. However, these models are a black box for their users. Some proposals have leveraged the weights assigned by the internal attention mechanisms of these models for interpretability purposes. However, whether the attention weights help the interpretability of the model is still a matter of debate, with positions in favor and against. This work proposes an attention-based interpretability mechanism to identify the most influential words for stances predicted using BERT-based models. We target stances expressed in Twitter using the Portuguese language and assess the proposed mechanism using a case study regarding stances on COVID-19 vaccination in the Brazilian context. The interpretation mechanism traces tokens’ attentions back to words, assigning a newly proposed metric referred to as absolute word attention. Through this metric, we assess several aspects to determine if we can find important words for the classification and with meaning for the domain. We developed a broad experimental setting that involved three datasets with tweets in Brazilian Portuguese and three BERT models with support for this language. Our results are encouraging, as we were able to identify 52-82% of words with high absolute attention contributing positively to stance classification. The interpretability mechanism proved to be helpful to understand the influence of words in the classification, and they revealed intrinsic properties of the domain and representative arguments of the stances.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88477038","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":"On the Impact of Dataset Size:A Twitter Classification Case Study","authors":"Thi-Huyen Nguyen, Hoang H. Nguyen, Zahra Ahmadi, Tuan-Anh Hoang, Thanh-Nam Doan","doi":"10.1145/3486622.3493960","DOIUrl":"https://doi.org/10.1145/3486622.3493960","url":null,"abstract":"The recent advent and evolution of deep learning models and pre-trained embedding techniques have created a breakthrough in supervised learning. Typically, we expect that adding more labeled data improves the predictive performance of supervised models. On the other hand, collecting more labeled data is not an easy task due to several difficulties, such as manual labor costs, data privacy, and computational constraint. Hence, a comprehensive study on the relation between training set size and the classification performance of different methods could be essentially useful in the selection of a learning model for a specific task. However, the literature lacks such a thorough and systematic study. In this paper, we concentrate on this relationship in the context of short, noisy texts from Twitter. We design a systematic mechanism to comprehensively observe the performance improvement of supervised learning models with the increase of data sizes on three well-known Twitter tasks: sentiment analysis, informativeness detection, and information relevance. Besides, we study how significantly better the recent deep learning models are compared to traditional machine learning approaches in the case of various data sizes. Our extensive experiments show (a) recent pre-trained models have overcome big data requirements, (b) a good choice of text representation has more impact than adding more data, and (c) adding more data is not always beneficial in supervised learning.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86590371","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":"A Subgraph Isomorphism-based Attack Towards Social Networks","authors":"Mengjiao Guo, Chi-Hung Chi, Hui Zheng, Jing He, Xiaoting Zhang","doi":"10.1145/3498851.3499024","DOIUrl":"https://doi.org/10.1145/3498851.3499024","url":null,"abstract":"It has been widely recognized that social network analysis of group relationships and behaviors come to thrive, so publicity social networks have gained growing attention from third-party individuals for academic researchers and advertisers. Anonymous versions are generally obtained from the naive anonymization mechanism through identity transformation to fend off attacks on socially sensitive information. The adversaries intend to implement person re-identification in anonymous data, and they generally possess a subset of social interaction information of the target user. In this way, a privacy breach could be achieved by exploiting the neighbourhood of the object's known structural information. Say, if one node's information is breached, other nodes’ private information will be compromised according to the detected structural information. Therefore, all the mentioned above are equivalent to the subgraph isomorphism problem to identify who is who in the social networks. Existing enumeration and indexing-related subgraph isomorphism methods cannot process matching problems with both large target and query graphs. Therefore, subgraph querying is a knotty problem pressing for a solution. In this work, we elaborate on the subgraph of structural attack. Our subgraph isomorphism-based method adopts a 3-stage framework for learning and refining structural correspondences over a large graph. First, we generate a set of candidate matches and compare the query graph with these candidate graphs over the corresponding number of vertex and edge, which can noticeably reduce the number of candidate graphs. Secondly, we employ the permutation theorem to evaluate the row sum of vertex and edge adjacency matrix of query graph and candidate graph. Lastly, our proposed scheme deploys the well-found equinumerosity theorem to verify if the query graph and candidate graph satisfy the isomorphic relationship. Solid evaluation criteria on time complexity verify the proposed attack strategy.","PeriodicalId":89230,"journal":{"name":"Proceedings. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87701349","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}