Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00083
Nitin Ramrakhiyani, Sangameshwar Patil, Manideep Jella, Alok Kumar, G. Palshikar
Cyber- physical systems are an important part of many industries such as the chemical process industry, manufac- turing industry, automobiles, and even sophisticated weaponry. Given the economic importance and influence of these systems, they have increasingly faced the cybersecurity attacks. In this paper, we provide a dataset of real-life security incident reports on cyber-physical systems annotated with entities and events that are important for analysing such security incidents. We analyze and identify the limitations of the 'Domain Objects' in Structured Threat Information Expression (STIX) standard as well as recent research literature for the entity type clas- sification schemes in cybersecurity domain. We propose an updated classification scheme for entity types in the cybersecurity domain. The enhanced coverage provided by the entity scheme is important for automated information extraction and natural language understanding of textual reports containing details of the cybersecurity incident reports. We use deep-learning based sequence labelling techniques and cybersecurity domain specific word embed dings to set up a benchmark for entity and event extraction for cyber- physical security incident report analysis. The annotated dataset of real-life industrial security incidents will be made available for research purpose.
{"title":"Extracting Entities and Events from Cyber-Physical Security Incident Reports","authors":"Nitin Ramrakhiyani, Sangameshwar Patil, Manideep Jella, Alok Kumar, G. Palshikar","doi":"10.1109/ICDMW58026.2022.00083","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00083","url":null,"abstract":"Cyber- physical systems are an important part of many industries such as the chemical process industry, manufac- turing industry, automobiles, and even sophisticated weaponry. Given the economic importance and influence of these systems, they have increasingly faced the cybersecurity attacks. In this paper, we provide a dataset of real-life security incident reports on cyber-physical systems annotated with entities and events that are important for analysing such security incidents. We analyze and identify the limitations of the 'Domain Objects' in Structured Threat Information Expression (STIX) standard as well as recent research literature for the entity type clas- sification schemes in cybersecurity domain. We propose an updated classification scheme for entity types in the cybersecurity domain. The enhanced coverage provided by the entity scheme is important for automated information extraction and natural language understanding of textual reports containing details of the cybersecurity incident reports. We use deep-learning based sequence labelling techniques and cybersecurity domain specific word embed dings to set up a benchmark for entity and event extraction for cyber- physical security incident report analysis. The annotated dataset of real-life industrial security incidents will be made available for research purpose.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121620742","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}
Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00113
Anne Marthe Sophie Ngo Bibinbe, A. J. Mahamadou, Michael Franklin Mbouopda, E. Nguifo
Anomaly detection in data streams comes with different technical challenges due to the data nature. The main challenges include storage limitations, the speed of data arrival, and concept drifts. In the literature, methods for mining data streams in order to detect anomalies have been proposed. While some methods focus on tackling a specific issue, other methods handle diverse problems but may have high complexity (time and memory). In the present work, we propose DragStream, a novel subsequence anomaly and concept drift detection algorithm for univariate data streams. DragStream extends the subsequence anomaly detection method for time series data Drag to streaming data. Furthermore, the new method is inspired by the well-known Matrix Profile, Drag, and MILOF which are respectively point and subsequence anomaly detection methods for time series and data streams. We conducted intensive experiments and statistical analysis to evaluate the performance of the proposed approach against existing methods. The results show that our method is competitive in performance while being linear in time and memory complexity. Finally, we provide an open-source implementation of the new method.
{"title":"DragStream: An Anomaly And Concept Drift Detector In Univariate Data Streams","authors":"Anne Marthe Sophie Ngo Bibinbe, A. J. Mahamadou, Michael Franklin Mbouopda, E. Nguifo","doi":"10.1109/ICDMW58026.2022.00113","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00113","url":null,"abstract":"Anomaly detection in data streams comes with different technical challenges due to the data nature. The main challenges include storage limitations, the speed of data arrival, and concept drifts. In the literature, methods for mining data streams in order to detect anomalies have been proposed. While some methods focus on tackling a specific issue, other methods handle diverse problems but may have high complexity (time and memory). In the present work, we propose DragStream, a novel subsequence anomaly and concept drift detection algorithm for univariate data streams. DragStream extends the subsequence anomaly detection method for time series data Drag to streaming data. Furthermore, the new method is inspired by the well-known Matrix Profile, Drag, and MILOF which are respectively point and subsequence anomaly detection methods for time series and data streams. We conducted intensive experiments and statistical analysis to evaluate the performance of the proposed approach against existing methods. The results show that our method is competitive in performance while being linear in time and memory complexity. Finally, we provide an open-source implementation of the new method.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123658573","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}
Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00090
Guojing Cong, Talia Ben-Naim, Victor Fung, Anshul Gupta, R. Neumann, Mathias Steiner
We present our research where attention mechanism is extensively applied to various aspects of graph neural net- works for predicting materials properties. As a result, surrogate models can not only replace costly simulations for materials screening but also formulate hypotheses and insights to guide further design exploration. We predict formation energy of the Materials Project and gas adsorption of crystalline adsorbents, and demonstrate the superior performance of our graph neural networks. Moreover, attention reveals important substructures that the machine learning models deem important for a material to achieve desired target properties. Our model is based solely on standard structural input files containing atomistic descriptions of the adsorbent material candidates. We construct novel methodological extensions to match the prediction accuracy of state-of-the-art models some of which were built with hundreds of features at much higher computational cost. We show that sophisticated neural networks can obviate the need for elaborate feature engineering. Our approach can be more broadly applied to optimize gas capture processes at industrial scale.
{"title":"Extensive Attention Mechanisms in Graph Neural Networks for Materials Discovery","authors":"Guojing Cong, Talia Ben-Naim, Victor Fung, Anshul Gupta, R. Neumann, Mathias Steiner","doi":"10.1109/ICDMW58026.2022.00090","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00090","url":null,"abstract":"We present our research where attention mechanism is extensively applied to various aspects of graph neural net- works for predicting materials properties. As a result, surrogate models can not only replace costly simulations for materials screening but also formulate hypotheses and insights to guide further design exploration. We predict formation energy of the Materials Project and gas adsorption of crystalline adsorbents, and demonstrate the superior performance of our graph neural networks. Moreover, attention reveals important substructures that the machine learning models deem important for a material to achieve desired target properties. Our model is based solely on standard structural input files containing atomistic descriptions of the adsorbent material candidates. We construct novel methodological extensions to match the prediction accuracy of state-of-the-art models some of which were built with hundreds of features at much higher computational cost. We show that sophisticated neural networks can obviate the need for elaborate feature engineering. Our approach can be more broadly applied to optimize gas capture processes at industrial scale.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121676321","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}
Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00041
R. Basiri, M. Popovic, Shehroz S. Khan
Diabetic Foot Ulcer (DFU) is a condition requiring constant monitoring and evaluations for treatment. DFU patient population is on the rise and will soon outpace the available health resources. Autonomous monitoring and evaluation of DFU wounds is a much-needed area in health care. In this paper, we evaluate and identify the most accurate feature extractor that is the core basis for developing a deep learning wound detection network. For the evaluation, we used mAP and F1-score on the publicly available DFU2020 dataset. A combination of UNet and EfficientNetb3 feature extractor resulted in the best evaluation among the 14 networks compared. UNet and Efficientnetb3 can be used as the classifier in the development of a comprehensive DFU domain-specific autonomous wound detection pipeline.
{"title":"Domain-Specific Deep Learning Feature Extractor for Diabetic Foot Ulcer Detection","authors":"R. Basiri, M. Popovic, Shehroz S. Khan","doi":"10.1109/ICDMW58026.2022.00041","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00041","url":null,"abstract":"Diabetic Foot Ulcer (DFU) is a condition requiring constant monitoring and evaluations for treatment. DFU patient population is on the rise and will soon outpace the available health resources. Autonomous monitoring and evaluation of DFU wounds is a much-needed area in health care. In this paper, we evaluate and identify the most accurate feature extractor that is the core basis for developing a deep learning wound detection network. For the evaluation, we used mAP and F1-score on the publicly available DFU2020 dataset. A combination of UNet and EfficientNetb3 feature extractor resulted in the best evaluation among the 14 networks compared. UNet and Efficientnetb3 can be used as the classifier in the development of a comprehensive DFU domain-specific autonomous wound detection pipeline.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"52 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120883848","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}
Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00013
Reda Khoufache, M. Dilmi, Hanene Azzag, Etienne Gofinnet, M. Lebbah
Artificial Intelligence (AI) in supermarkets is moving fast with the recent advances in deep learning. One important project in the retail sector is the development of AI solutions for smart stores, mainly to improve product recognition. In this paper, we present a new framework to address the multi-view image classification using multiple clustering. The proposed framework combines a pre-trained Vision Transformer with a Bayesian Non-Parametric multiple clustering. In this work, we propose an M CM C- based inference approach to learn the column-partition and the row-partitions. This method infers multiple clustering solutions and allows to find automatically the number of clusters. Our method provides interesting results on a multi-view image dataset and emphasizes, on one hand, the power of pre-trained Vision Transformers combined with the multiple clustering algorithm, on the other hand, the usefulness of the Bayesian Non-Parametric modeling, which automatically performs a model selection.
随着深度学习的最新进展，超市中的人工智能(AI)正在迅速发展。零售领域的一个重要项目是为智能商店开发人工智能解决方案，主要是为了提高产品识别。本文提出了一种新的基于多聚类的多视图图像分类框架。该框架将预训练的视觉转换器与贝叶斯非参数多聚类相结合。在这项工作中，我们提出了一种基于M - CM - C的推理方法来学习列分区和行分区。该方法推断出多个聚类解决方案，并允许自动查找聚类的数量。我们的方法在多视图图像数据集上提供了有趣的结果，并且一方面强调了预先训练的视觉变形器与多聚类算法相结合的强大功能，另一方面强调了贝叶斯非参数建模的有用性，该建模可以自动执行模型选择。
{"title":"Emerging properties from Bayesian Non-Parametric for multiple clustering: Application for multi-view image dataset","authors":"Reda Khoufache, M. Dilmi, Hanene Azzag, Etienne Gofinnet, M. Lebbah","doi":"10.1109/ICDMW58026.2022.00013","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00013","url":null,"abstract":"Artificial Intelligence (AI) in supermarkets is moving fast with the recent advances in deep learning. One important project in the retail sector is the development of AI solutions for smart stores, mainly to improve product recognition. In this paper, we present a new framework to address the multi-view image classification using multiple clustering. The proposed framework combines a pre-trained Vision Transformer with a Bayesian Non-Parametric multiple clustering. In this work, we propose an M CM C- based inference approach to learn the column-partition and the row-partitions. This method infers multiple clustering solutions and allows to find automatically the number of clusters. Our method provides interesting results on a multi-view image dataset and emphasizes, on one hand, the power of pre-trained Vision Transformers combined with the multiple clustering algorithm, on the other hand, the usefulness of the Bayesian Non-Parametric modeling, which automatically performs a model selection.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123678262","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}
Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00045
Toru Sasaki, Tomonari Masada
Automated Essay Scoring (AES) refers to a set of processes that automatically assigns grades to student-written essays with machine learning models. Existing AES models are mostly trained prompt-specifically with supervised learning, which requires the essay prompt to be accessible to the system vendor at the time of model training. However, essay prompts for high-stakes testing should usually be kept confidential before the test date, which demands the model to be cross-promptly trainable with pre-scored essay data already in hands. Document embeddings obtained from pretrained language models such as Sentence-BERT (sbert) are primarily expected to represent the semantic content of the text. We hypothesize SBERT embeddings also contain assessment-relevant elements that are extractable by document embedding decomposition through Principal Component Analysis (PCA) enhanced with Normalized Discounted Cumulative Gain (nDCG) measurement. The identified evaluative elements in the entire embedding space of the source essays are then cross-promptly transferred to the target essays written on different prompts for binary clustering task of dividing high/low-scored groups. The result implies non-finetuned SBERT already contains evaluative elements to distinguish good and bad essays.
{"title":"Sentence-BERT Distinguishes Good and Bad Essays in Cross-prompt Automated Essay Scoring","authors":"Toru Sasaki, Tomonari Masada","doi":"10.1109/ICDMW58026.2022.00045","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00045","url":null,"abstract":"Automated Essay Scoring (AES) refers to a set of processes that automatically assigns grades to student-written essays with machine learning models. Existing AES models are mostly trained prompt-specifically with supervised learning, which requires the essay prompt to be accessible to the system vendor at the time of model training. However, essay prompts for high-stakes testing should usually be kept confidential before the test date, which demands the model to be cross-promptly trainable with pre-scored essay data already in hands. Document embeddings obtained from pretrained language models such as Sentence-BERT (sbert) are primarily expected to represent the semantic content of the text. We hypothesize SBERT embeddings also contain assessment-relevant elements that are extractable by document embedding decomposition through Principal Component Analysis (PCA) enhanced with Normalized Discounted Cumulative Gain (nDCG) measurement. The identified evaluative elements in the entire embedding space of the source essays are then cross-promptly transferred to the target essays written on different prompts for binary clustering task of dividing high/low-scored groups. The result implies non-finetuned SBERT already contains evaluative elements to distinguish good and bad essays.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128597868","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}
Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00021
A. Ramkissoon, Vijayanandh Rajamanickam, W. Goodridge
The existence of fake videos is a problem that is challenging today's social media-enabled world. There are many classifications for fake videos with one of the most popular being DeepFakes. Detecting such fake videos is a challenging issue. This research attempts to comprehend the characteristics that belong to DeepFake videos. In attempting to understand DeepFake videos this work investigates the characteristics of the video that make them unique. As such this research uses scene and texture detection to develop a unique feature set containing 19 data features which is capable of detecting whether a video is a DeepFake or not. This study validates the feature set using a standard dataset of the features relating to the characteristics of the video. These features are analysed using a classification machine learning model. The results of these experiments are examined using four evaluation methodologies. The analysis reveals positive performance with the use of the ML method and the feature set. From these results, it can be ascertained that using the proposed feature set, a video can be predicted as a DeepFake or not and as such prove the hypothesis that there exists a correlation between the characteristics of a video and its genuineness, i.e., whether or not a video is a DeepFake.
{"title":"Scene and Texture Based Feature Set for DeepFake Video Detection","authors":"A. Ramkissoon, Vijayanandh Rajamanickam, W. Goodridge","doi":"10.1109/ICDMW58026.2022.00021","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00021","url":null,"abstract":"The existence of fake videos is a problem that is challenging today's social media-enabled world. There are many classifications for fake videos with one of the most popular being DeepFakes. Detecting such fake videos is a challenging issue. This research attempts to comprehend the characteristics that belong to DeepFake videos. In attempting to understand DeepFake videos this work investigates the characteristics of the video that make them unique. As such this research uses scene and texture detection to develop a unique feature set containing 19 data features which is capable of detecting whether a video is a DeepFake or not. This study validates the feature set using a standard dataset of the features relating to the characteristics of the video. These features are analysed using a classification machine learning model. The results of these experiments are examined using four evaluation methodologies. The analysis reveals positive performance with the use of the ML method and the feature set. From these results, it can be ascertained that using the proposed feature set, a video can be predicted as a DeepFake or not and as such prove the hypothesis that there exists a correlation between the characteristics of a video and its genuineness, i.e., whether or not a video is a DeepFake.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128776656","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}
Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00089
Peng Zhou, Yunyun Zhang, Yuan-Ting Yan, Shu Zhao
Feature selection aims to select an optimal minimal feature subset from the original datasets and has become an indispensable preprocessing component before data mining and machine learning, especially in the era of big data. Most feature selection methods implicitly assume that we can know the feature type (categorical, numerical, or mixed) before learning, then design corresponding measurements to calculate the correlation between features. However, in practical applications, features may be generated dynamically and arrive one by one over time, which we call streaming features. Most existing streaming feature selection methods assume that all dynamically generated features are the same type or assume we can know the feature type for each new arriving feature on the fly, but this is unreasonable and unrealistic. Therefore, this paper firstly studies a practical issue of Unknown Type Streaming Feature Selection and proposes a new method to handle it, named UT-SFS. Extensive experimental results indicate the effectiveness of our new method. UT-SFS is nonparametric and does not need to know the feature type before learning, which aligns with practical application needs.
{"title":"Unknown Type Streaming Feature Selection via Maximal Information Coefficient","authors":"Peng Zhou, Yunyun Zhang, Yuan-Ting Yan, Shu Zhao","doi":"10.1109/ICDMW58026.2022.00089","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00089","url":null,"abstract":"Feature selection aims to select an optimal minimal feature subset from the original datasets and has become an indispensable preprocessing component before data mining and machine learning, especially in the era of big data. Most feature selection methods implicitly assume that we can know the feature type (categorical, numerical, or mixed) before learning, then design corresponding measurements to calculate the correlation between features. However, in practical applications, features may be generated dynamically and arrive one by one over time, which we call streaming features. Most existing streaming feature selection methods assume that all dynamically generated features are the same type or assume we can know the feature type for each new arriving feature on the fly, but this is unreasonable and unrealistic. Therefore, this paper firstly studies a practical issue of Unknown Type Streaming Feature Selection and proposes a new method to handle it, named UT-SFS. Extensive experimental results indicate the effectiveness of our new method. UT-SFS is nonparametric and does not need to know the feature type before learning, which aligns with practical application needs.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125894631","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}
Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00070
Minqiang Yang, Xinqi Liu, Chengsheng Mao, Bin Hu
Sentiment analysis has become increasingly important in natural language processing (NLP). Recent efforts have been devoted to the graph convolutional network (GCN) due to its advantages in handling the complex information. However, the improvement of GCN in NLP is hindered because the pretrained word vectors do not fit well in various contexts and the traditional edge building methods are not suited well for the long and complex context. To address these problems, we propose the LSTM-GCN model to contextualize the pretrained word vectors and extract the sentiment representations from the complex texts. Particularly, LSTM-GCN captures the sentiment feature representations from multiple different perspectives including context and syntax. In addition to extracting contextual representation from pretrained word vectors, we utilize the dependency parser to analyse the dependency correlation between each word to extract the syntax representation. For each text, we build a graph with each word in the text as a node. Besides the edges between the neighboring words, we also connect the nodes with dependency correlation to capture syntax representations. Moreover, we introduce the message passing mechanism (MPM) which allows the nodes to update their representation by extract information from its neighbors. Also, to improve the message passing performance, we set the edges to be trainable and initialize the edge weights with the pointwise mutual information (PMI) method. The results of the experiments show that our LSTM-GCN model outperforms several state-of-the-art models. And extensive experiments validate the rationality and effectiveness of our model.
{"title":"Graph Convolutional Networks with Dependency Parser towards Multiview Representation Learning for Sentiment Analysis","authors":"Minqiang Yang, Xinqi Liu, Chengsheng Mao, Bin Hu","doi":"10.1109/ICDMW58026.2022.00070","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00070","url":null,"abstract":"Sentiment analysis has become increasingly important in natural language processing (NLP). Recent efforts have been devoted to the graph convolutional network (GCN) due to its advantages in handling the complex information. However, the improvement of GCN in NLP is hindered because the pretrained word vectors do not fit well in various contexts and the traditional edge building methods are not suited well for the long and complex context. To address these problems, we propose the LSTM-GCN model to contextualize the pretrained word vectors and extract the sentiment representations from the complex texts. Particularly, LSTM-GCN captures the sentiment feature representations from multiple different perspectives including context and syntax. In addition to extracting contextual representation from pretrained word vectors, we utilize the dependency parser to analyse the dependency correlation between each word to extract the syntax representation. For each text, we build a graph with each word in the text as a node. Besides the edges between the neighboring words, we also connect the nodes with dependency correlation to capture syntax representations. Moreover, we introduce the message passing mechanism (MPM) which allows the nodes to update their representation by extract information from its neighbors. Also, to improve the message passing performance, we set the edges to be trainable and initialize the edge weights with the pointwise mutual information (PMI) method. The results of the experiments show that our LSTM-GCN model outperforms several state-of-the-art models. And extensive experiments validate the rationality and effectiveness of our model.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121063083","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}
Pub Date : 2022-11-01DOI: 10.1109/ICDMW58026.2022.00075
Yanlin Qi, Fuyin Lai, Guoting Chen, Wensheng Gan
This paper aims to propose an effective algorithm to discover valuable patterns by applying the fuzzy method to the RFM model. RFM analysis is a common method in customer relationship management, through which we can identify valuable customer groups. By combining RFM analysis with frequent pattern mining, valuable RFM - patterns can be found from the RFM-pattern-tree, such as the RFMP-growth algorithm. Aiming to mine patterns that have quantitative relationships among items, we introduce the fuzzy method in the RFM model, and we present a fuzzy - Rfu - tree algorithm in which a new pruning strategy is proposed to prune candidate patterns. Experiments show the effectiveness of the new algorithm. The new algorithm guarantees a high overlap degree with the RFM-patterns gen-erated by RFMP-growth, with more valuable information (with additional fuzzy level) in the mined patterns.
{"title":"Mining Valuable Fuzzy Patterns via the RFM Model","authors":"Yanlin Qi, Fuyin Lai, Guoting Chen, Wensheng Gan","doi":"10.1109/ICDMW58026.2022.00075","DOIUrl":"https://doi.org/10.1109/ICDMW58026.2022.00075","url":null,"abstract":"This paper aims to propose an effective algorithm to discover valuable patterns by applying the fuzzy method to the RFM model. RFM analysis is a common method in customer relationship management, through which we can identify valuable customer groups. By combining RFM analysis with frequent pattern mining, valuable RFM - patterns can be found from the RFM-pattern-tree, such as the RFMP-growth algorithm. Aiming to mine patterns that have quantitative relationships among items, we introduce the fuzzy method in the RFM model, and we present a fuzzy - Rfu - tree algorithm in which a new pruning strategy is proposed to prune candidate patterns. Experiments show the effectiveness of the new algorithm. The new algorithm guarantees a high overlap degree with the RFM-patterns gen-erated by RFMP-growth, with more valuable information (with additional fuzzy level) in the mined patterns.","PeriodicalId":146687,"journal":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126541686","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：