{"title":"E-Commerce Merchant Classification using Website Information","authors":"Galuh Tunggadewi Sahid, Rahmad Mahendra, I. Budi","doi":"10.1145/3326467.3326486","DOIUrl":"https://doi.org/10.1145/3326467.3326486","url":null,"abstract":"With the rapid growth of the e-commerce landscape, classifying e-commerce merchants has become an important task as it is an integral part of various processes in e-commerce. One of the examples is merchant on boarding, where the category of an e-commerce merchant has proven to be a good indicator of the risk of the merchant. However, since most of e-commerce businesses do not have brick-and-mortar stores from which we can assess it directly, the only source of information regarding the merchant itself is its website. Thus, we can view this problem as a web classification problem, where we classify e-commerce websites into a category. In this research, we aim to build an end-to-end classification system for e-commerce websites. There are a few challenges such as the number of pages to be processed, imbalanced dataset, and the language of e-commerce websites that can be mixed language. We built a website classification system and experimented with case study of Indonesian and English e-commerce webs, that are classified into 37 different categories. Our best result achieved an F-score of 0.83.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115356018","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}
Jongbeen Han, Heemin Kim, Hyeonsang Eom, J. Coignard, Kesheng Wu, Yongseok Son
{"title":"Enabling SQL-Query Processing for Ethereum-based Blockchain Systems","authors":"Jongbeen Han, Heemin Kim, Hyeonsang Eom, J. Coignard, Kesheng Wu, Yongseok Son","doi":"10.1145/3326467.3326479","DOIUrl":"https://doi.org/10.1145/3326467.3326479","url":null,"abstract":"A blockchain is designed to make consistent and reliable agreement in an unreliable and decentralized environment. It also permits processing transactions, making smart contracts, which allows end users to perform the contracts without any intermediate entities. However, there are some challenges in retrieving the state in a smart contract on the blockchain. For example, an external database or user-defined data structures can be used to retrieve the data from a smart contract in a range, which can increase the management overhead and decrease the overall performance of the blockchain system. In this paper, we propose a scheme that enables SQL query operations in a blockchain system. In our proposed scheme, the register and query managers provide fast retrieval of range data without any user-defined data structure, and management at low cost without any external database, respectively. We have implemented our scheme on quorum which is an Ethereum-based blockchain system and evaluated it using a synthetic benchmark. The experimental results show that our system can improve the search performance up to about 22x compared with the existing system with low memory usage.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116417229","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":"Hypercat JSON-LD: A Semantically Enriched Catalogue Format for IoT","authors":"M. Georgiou, Ilias Tachmazidis, G. Antoniou","doi":"10.1145/3326467.3326477","DOIUrl":"https://doi.org/10.1145/3326467.3326477","url":null,"abstract":"The rapidly increasing number of sensor networks and smart devices contributed to the generation of a huge amount of information. Information that is generated by various sources and is published in different formats high-lights interoperability as one of the key prerequisites for the success of the Internet of Things (IoT). Hypercat is a specification defining a lightweight JSON-based hypermedia catalogue, designed to serve the needs of the industry. In this paper, we extend the existing work on semantic enrichment of Hypercat by defining a JSON-LD based catalogue. The proposed JSON-LD specification provides a mapping mechanism between JSON and JSON-LD catalogues, while highlighting the fact that JSON-LD could be seamlessly adopted by the Hypercat community.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124007351","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":"An Effective Deep Learning Framework for Detecting Misconduct of the Trucker","authors":"Yu-Chia Chang, Huan Chen, Chun-Wei Tsai","doi":"10.1145/3326467.3326482","DOIUrl":"https://doi.org/10.1145/3326467.3326482","url":null,"abstract":"The traffic risks include malfunction of gears in the vehicle and some human misconducts while on the road. These misconducts of driver contain using the mobile phone, smoking, watching videos, reading books, and so forth. To prevent drivers from danger, in this paper, we will present an effective system to detect whether the drivers are doing those behaviors while driving by using the deep learning technologies. The proposed system adopts two different neural network architectures to improve its accuracy rate that are multilayer perceptron (MLP) and convolutional neural network (CNN). As expected, by training the video data from cameras installed in the truck, the proposed system could possibly distinguish the misconduct if the drivers are doing danger behaviors. The result of this paper shows that the proposed system practically provides a solution to recognize misconducts of the trucker with 90% accuracy of detecting abnormal situations.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132108353","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":"Context-Based Rating Prediction using Collaborative Filtering and Linked Open Data","authors":"V. K. Sejwal, M. Abulaish","doi":"10.1145/3326467.3326489","DOIUrl":"https://doi.org/10.1145/3326467.3326489","url":null,"abstract":"Linked Open Data (LOD) consists of various knowledgebases, such as DBpedia, Yago, and Freebase, and uses structured data as features to conceptualize a domain of interest. During last few years, many researchers have shown how LOD can be utilized in various applications, including recommender systems that are used to map items and users generally on the basis of interest and similarity parameters. However, contextual features play an important role to improve the effectiveness of the recommender systems. In this paper, we propose a contextual feature-based rating prediction and recommendation technique using item-based collaborative filtering and LOD. To this end, we have generated a RDF graph representing items and their contextual features, which help to determine context-based similar items for recommendation using graph matching techniques. In order to extract contextual features for item profiling, we have used LOD and two famous movie data sources, Rotten Tomatoes and IMDB. We also propose a rating prediction model to predict the rating of the non-rated items with the help of the RDF graph and item-based collaborative filtering. The proposed approach is evaluated using mean absolute error and root mean square error, and performs significantly better in comparison to some of the standard baseline methods.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"138 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120883497","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":"Robust Active Learning of Expressive Linkage Rules","authors":"Anna Primpeli, Christian Bizer","doi":"10.1145/3326467.3326484","DOIUrl":"https://doi.org/10.1145/3326467.3326484","url":null,"abstract":"The goal of entity resolution, also known as duplicate detection and record linkage, is to identify all records in one or more data sets that refer to the same real-world entity. To achieve this goal, matching rules, encoding the matching patterns in the data, can be learned with the help of manually annotated record pairs. Active learning for entity resolution aims to minimize the human labeling effort by including the human into the learning loop and by selecting the most informative pairs for labeling. While active learning methods are quite successful at reducing the human labeling effort, we show that their performance decreases when applied to data sets having a large number of sparse attributes. We evaluate the ActiveGenLink active learning method using e-commerce data sets with such characteristics and observe that it is prone to suboptimal convergence points, thus producing highly varying results in different runs of the same experiment. In this paper we present our ongoing work on building a robust active learning method which is able to tackle the instability. Our method applies unsupervised matching of the record pairs as a first step. The unsupervised matching results are used afterwards for bootstrapping the active learning process and for preventing it from converging to suboptimal matching rules. The evaluation shows that the proposed method increases the robustness of the active learning process as it reduces the variation of the results of different runs by 10% to 16%.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123947249","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 Probabilistic Model for Collaborative Filtering","authors":"Zuoquan Lin, Hanxuan Chen","doi":"10.1145/3326467.3326472","DOIUrl":"https://doi.org/10.1145/3326467.3326472","url":null,"abstract":"We propose a probabilistic model that uses the early data to generate the prior distribution and the recent data to capture the change of the states of both users and items in collaborative filtering system. It keeps updating every time it receives new data and has a constant limit of the time cost of every updating, which is suitable to deal with large scale data for online recommendation. Experiments on real datasets show the improvement performance of our model over the existing time-aware recommender systems.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126930279","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":"Synthesizing N-ary Relations from Web Tables","authors":"O. Lehmberg, Christian Bizer","doi":"10.1145/3326467.3326480","DOIUrl":"https://doi.org/10.1145/3326467.3326480","url":null,"abstract":"The Web contains a large number of relational HTML tables, which cover a multitude of different, often very specific topics. This rich pool of data has motivated a growing body of research on methods that use web table data to extend local tables with additional attributes or add missing facts to knowledge bases. Nearly all existing approaches for these tasks are limited to the extraction of binary relations from web tables, e.g. an unemployment number may only depend on the state. Inspecting randomly chosen tables on the Web quickly reveals that many relations in the tables are non-binary, e.g. unemployment numbers also depend on the point in time and the profession. Treating such n-ary relations as binary leads to data that cannot be interpreted correctly. The extraction of n-ary relations from web tables is complicated by two factors: 1. important attributes might be stated outside of the table; 2. relational web tables are usually too small for functional dependency discovery. This paper presents a method to synthesize n-ary relations from web tables for the use case of knowledge base extension. The method exploits information from the page around the table and stitches (combines) multiple tables from the same website. We apply the method to a corpus of 5 million web tables originating from 80 thousand different web sites and find that 38% of the synthesized relations are non-binary. We find different relations for the same dependent attribute, e.g. relations providing unemployment numbers based on time, location, or profession. By identifying groups of websites which provide these relations, we lay the foundation for applications in knowledge base augmentation and data search, which allow for a specific selection of relations that determine an attribute according to the applications' data requirements.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116822993","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":"Computing the Linguistic-Based Cues of Fake News in the Philippines Towards its Detection","authors":"A. Fernández, M. Devaraj","doi":"10.1145/3326467.3326490","DOIUrl":"https://doi.org/10.1145/3326467.3326490","url":null,"abstract":"Fake news deliberately beguiles its consumers to accept false or biased ideologies. But as menacing as it sounds to the society, it poses a good classification problem to computer science. This paper presents the disparity in writing style between legitimate news and fake news in the Philippines, and how effective these are as machine learning features. To capacitate this, credible news samples, as well as fake news samples in the Philippines were harvested online. The best feature set was consistent across all experiments and attained a precision of 94% on both the feature selection process and the test set of the final model. It also attained a precision of 93% on a more recent data collected, which was not part of the initial corpus constructed. Furthermore, this paper exhibits how legitimate and fake news in the Philippines can be differentiated just by their headline or content at a precision of 87% and 88%, respectively.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115472315","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":"Cultural Intelligence and ARCS Model for Digital Era","authors":"Jong-Youl Hong, H. Ko, J. Kim","doi":"10.1145/3326467.3326495","DOIUrl":"https://doi.org/10.1145/3326467.3326495","url":null,"abstract":"The main aim of this study is to explore the theoretical foundations necessary for the development of cross-cultural training programs by integrating the ARCS motivation model into the cultural intelligence model to strengthen the motivation of the participants. Firstly, the cultural intelligence self-test, which can be directly applied to the cross-cultural training program, has been newly designed and presented based on a comprehensive analysis of the available research results. Furthermore, the ARCS model was introduced to the cultural intelligence learning process to suggest the ways to enhance the learning effect. In the design of cultural intelligence training programs, it is expected to be a more effective process by actively using the pedagogical research achievements called the ARCS model.","PeriodicalId":219310,"journal":{"name":"Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics","volume":"349 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122336229","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}