Pub Date : 2022-03-01DOI: 10.1109/CDMA54072.2022.00025
Rafi Ud Daula Refat, Abdulrahman Abu Elkhail, H. Malik
The Controller Area Network (CAN) protocol is the most commonly used communication protocol for in-vehicle networks due to its simplicity, efficiency and robustness. However, the CAN protocol is vulnerable to malicious attacks because it lacks basic security features such as message ID authentication, access control and message verification. Specifically, CAN pro-tocol fails to provide protection against message injection at-tacks. This paper presents a novel lightweight Intrusion Detection System (IDS) that translates CAN traffic into a mathematical abstraction i.e. temporal graph and then applies neighborhood-based graph similarity technique to detect CAN bus intrusions. The performance of the proposed approach is evaluated on a dataset from a real vehicle. The dataset consists of three types of message injection attack including spoofing, fuzzy and DoS attack is used for performance evaluation. Experimental results indicate that the proposed IDS can successfully detect these attacks with high detection accuracy. Specifically, the proposed IDS achieves detection accuracy of 96.01% as compared to best case scenario detection accuracy of 90.16% for existing state-of-the-art.
{"title":"A Lightweight Intrusion Detection System for CAN Protocol Using Neighborhood Similarity","authors":"Rafi Ud Daula Refat, Abdulrahman Abu Elkhail, H. Malik","doi":"10.1109/CDMA54072.2022.00025","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00025","url":null,"abstract":"The Controller Area Network (CAN) protocol is the most commonly used communication protocol for in-vehicle networks due to its simplicity, efficiency and robustness. However, the CAN protocol is vulnerable to malicious attacks because it lacks basic security features such as message ID authentication, access control and message verification. Specifically, CAN pro-tocol fails to provide protection against message injection at-tacks. This paper presents a novel lightweight Intrusion Detection System (IDS) that translates CAN traffic into a mathematical abstraction i.e. temporal graph and then applies neighborhood-based graph similarity technique to detect CAN bus intrusions. The performance of the proposed approach is evaluated on a dataset from a real vehicle. The dataset consists of three types of message injection attack including spoofing, fuzzy and DoS attack is used for performance evaluation. Experimental results indicate that the proposed IDS can successfully detect these attacks with high detection accuracy. Specifically, the proposed IDS achieves detection accuracy of 96.01% as compared to best case scenario detection accuracy of 90.16% for existing state-of-the-art.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120962496","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00017
Nabiollah Mansouri, M. Soui, Ibrahim Alhassan, Mourad Abed
Nowadays, social media like Twitter, play a vital role in our life since it is a source of swapping views, thoughts, and feelings towards many issues such as the global pandemic covid-19. Nevertheless, it can a source of diffusion of fake news which can affect negatively the opinions of many people and even change their thoughts behind a lot of sensitive situations such as the COVID-19 vaccines. In this context, it is crucial for public health agencies to understand and identify people's opinions and views toward COVID-19 vaccines. To this end, we propose our model to classify the tweets of people into three classes, negative, neutral, and positive. In fact, we considered a large dataset extracted from Twitter includes 174490 tweets. Tweet analysis was conducted by TextBlob to categorize the sentiment and the Bidirectional LSTM model to classify the sentiments. The proposed model was compared with other studied machine learning classifiers and deep learning algorithms. The aim of this work also is to select the best model between the studied model that is suitable for the sentiment analysis for COVID-19 vaccines. BiLSTM outperformed the other studied models with ahigh accuracy rate of 94.12%.
{"title":"TextBlob and BiLSTM for Sentiment analysis toward COVID-19 vaccines","authors":"Nabiollah Mansouri, M. Soui, Ibrahim Alhassan, Mourad Abed","doi":"10.1109/CDMA54072.2022.00017","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00017","url":null,"abstract":"Nowadays, social media like Twitter, play a vital role in our life since it is a source of swapping views, thoughts, and feelings towards many issues such as the global pandemic covid-19. Nevertheless, it can a source of diffusion of fake news which can affect negatively the opinions of many people and even change their thoughts behind a lot of sensitive situations such as the COVID-19 vaccines. In this context, it is crucial for public health agencies to understand and identify people's opinions and views toward COVID-19 vaccines. To this end, we propose our model to classify the tweets of people into three classes, negative, neutral, and positive. In fact, we considered a large dataset extracted from Twitter includes 174490 tweets. Tweet analysis was conducted by TextBlob to categorize the sentiment and the Bidirectional LSTM model to classify the sentiments. The proposed model was compared with other studied machine learning classifiers and deep learning algorithms. The aim of this work also is to select the best model between the studied model that is suitable for the sentiment analysis for COVID-19 vaccines. BiLSTM outperformed the other studied models with ahigh accuracy rate of 94.12%.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126928863","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00010
K. Alheeti, Abdulkareem Alzahrani, Najmaddin Khoshnaw, Duaa Al-Dosary
In recent years, deep generative networks have reinforced the need for caution while consuming different formats of digital information. One method of deepfake generation involves the insertion and removal of tumors from medical scans. Significant drains on hospital resources or even loss of life are the consequences of failure to detect medical deepfakes. This research attempts to evaluate machine learning algorithms and pre-trained deep neural networks' (DNN) ability to distinguish tampered data and authentic data. Moreover, this research aims to classify cancer scans based on DNN. The experimental results show that the proposed method based on using DNN can enhance performance detection. Furthermore, the proposed system increased the detection accuracy rate and reduced the number of false alarms.
{"title":"Intelligent Deep Detection Method for Malicious Tampering of Cancer Imagery","authors":"K. Alheeti, Abdulkareem Alzahrani, Najmaddin Khoshnaw, Duaa Al-Dosary","doi":"10.1109/CDMA54072.2022.00010","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00010","url":null,"abstract":"In recent years, deep generative networks have reinforced the need for caution while consuming different formats of digital information. One method of deepfake generation involves the insertion and removal of tumors from medical scans. Significant drains on hospital resources or even loss of life are the consequences of failure to detect medical deepfakes. This research attempts to evaluate machine learning algorithms and pre-trained deep neural networks' (DNN) ability to distinguish tampered data and authentic data. Moreover, this research aims to classify cancer scans based on DNN. The experimental results show that the proposed method based on using DNN can enhance performance detection. Furthermore, the proposed system increased the detection accuracy rate and reduced the number of false alarms.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124261866","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00019
Pablo Adames, Sourabh Mokhasi, Y. Pauchard, Mohammed Moshirpour, Camilo Rostoker
This work explores the effect of the quality of inferred user profiles on the accuracy of charitable recommendations when using an item-based collaborative filter algorithm. A gap was identified in the literature with respect to the application of charitable recom-mendation systems in the absence of rich user profiles. This paper introduces an approach to generate relevant recommendations when neither user profiles nor feedback on donation preferences is available. The discovery of user preferences is achieved via the construction of implicit ratings computed from custom feature engineering, while the sparsity of item and user ratings was addressed with a dimension reduction strategy based on dual-autoencoders from a commercial machine learning platform. Our analysis shows the magnitude and sensitivity of the relationship between the relevance of the recommendations and the average number of donations per user. Raw data for this research was provided by a leading online donation platform and contains 24 million anonymous donations to 165 thousand unique causes from over 1.2 million users. We find that the most effective way to increase the relevance of recommendations by a factor of 2 at any top- k value is to train the collaborative filter with users that have at least 50 donations in the data set. As a result, the training set for the collaborative filter is restricted to 8% of the original users, 70% of the companies, 49% of the causes, and 70% of the original countries where users making donations reside.
{"title":"Improving Relevance in a Recommendation System to Suggest Charities without Explicit User Profiles Using Dual-Autoencoders","authors":"Pablo Adames, Sourabh Mokhasi, Y. Pauchard, Mohammed Moshirpour, Camilo Rostoker","doi":"10.1109/CDMA54072.2022.00019","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00019","url":null,"abstract":"This work explores the effect of the quality of inferred user profiles on the accuracy of charitable recommendations when using an item-based collaborative filter algorithm. A gap was identified in the literature with respect to the application of charitable recom-mendation systems in the absence of rich user profiles. This paper introduces an approach to generate relevant recommendations when neither user profiles nor feedback on donation preferences is available. The discovery of user preferences is achieved via the construction of implicit ratings computed from custom feature engineering, while the sparsity of item and user ratings was addressed with a dimension reduction strategy based on dual-autoencoders from a commercial machine learning platform. Our analysis shows the magnitude and sensitivity of the relationship between the relevance of the recommendations and the average number of donations per user. Raw data for this research was provided by a leading online donation platform and contains 24 million anonymous donations to 165 thousand unique causes from over 1.2 million users. We find that the most effective way to increase the relevance of recommendations by a factor of 2 at any top- k value is to train the collaborative filter with users that have at least 50 donations in the data set. As a result, the training set for the collaborative filter is restricted to 8% of the original users, 70% of the companies, 49% of the causes, and 70% of the original countries where users making donations reside.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122687204","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 : 2022-03-01DOI: 10.1109/cdma54072.2022.00005
Lahouari Ghout, B. Qureshi, T. Saba, H. Malik
{"title":"7th International Conference on Data Science and Machine Learning Applications (CDMA2022)","authors":"Lahouari Ghout, B. Qureshi, T. Saba, H. Malik","doi":"10.1109/cdma54072.2022.00005","DOIUrl":"https://doi.org/10.1109/cdma54072.2022.00005","url":null,"abstract":"","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126393458","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00013
Haneen Alokasi, M. B. Ahmad
With the fast improvement of classification networks, many of these networks are being in use as backbones of semantic segmentation networks to improve the accuracy. Using different classification networks as the backbone of the same semantic segmentation network may show different accuracy performance. This paper selected the sandstone dataset and self-driving cars dataset to compare the accuracy performance differences of VGG-16, ResNet-34, and Inceptionv3 as the backbone of UNet, where the original encoder of the UNet is replaced by a backbone. The three backbone networks are imported from Segmentation Models library, and they have weights trained on ImageNet dataset. The best accuracy performance of the semantic segmentation network on the sandstone dataset is when VGG-16 is used as the backbone, it achieved 76.22% MIoU. On the other hand, the highest accuracy performance of the semantic segmentation network on self-driving cars dataset is 75.47% MIoU, achieved when Inceptionv3 is used as the backbone. However, the accuracy is improved when using all the three backbones with both datasets, compared to the accuracy performance of the UNet without using any backbone network.
{"title":"The Accuracy Performance of Semantic Segmentation Network with Different Backbones","authors":"Haneen Alokasi, M. B. Ahmad","doi":"10.1109/CDMA54072.2022.00013","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00013","url":null,"abstract":"With the fast improvement of classification networks, many of these networks are being in use as backbones of semantic segmentation networks to improve the accuracy. Using different classification networks as the backbone of the same semantic segmentation network may show different accuracy performance. This paper selected the sandstone dataset and self-driving cars dataset to compare the accuracy performance differences of VGG-16, ResNet-34, and Inceptionv3 as the backbone of UNet, where the original encoder of the UNet is replaced by a backbone. The three backbone networks are imported from Segmentation Models library, and they have weights trained on ImageNet dataset. The best accuracy performance of the semantic segmentation network on the sandstone dataset is when VGG-16 is used as the backbone, it achieved 76.22% MIoU. On the other hand, the highest accuracy performance of the semantic segmentation network on self-driving cars dataset is 75.47% MIoU, achieved when Inceptionv3 is used as the backbone. However, the accuracy is improved when using all the three backbones with both datasets, compared to the accuracy performance of the UNet without using any backbone network.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114808749","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00038
Gourango Modak, S. Das, Md. Ajharul Islam Miraj, Md. Kishor Morol
While deep learning-based image reconstruction methods have shown significant success in removing objects from pictures, they have yet to achieve acceptable results for attributing consistency to gender, ethnicity, expression, and other characteristics like the topological structure of the face. The purpose of this work is to extract the mask region from a masked image and rebuild the area that has been detected. This problem is complex because (i) it is difficult to determine the gender of an image hidden behind a mask, which causes the network to become confused and reconstruct the male face as a female or vice versa; (ii) we may receive images from multiple angles, making it extremely difficult to maintain the actual shape, topological structure of the face and a natural image; and (iii) there are problems with various mask forms because, in some cases, the area of the mask cannot be anticipated precisely; certain parts of the mask remain on the face after completion. To solve this complex task, we split the problem into three phases: landmark detection, object detection for the targeted mask area, and inpainting the addressed mask region. To begin, to solve the first problem, we have used gender classification, which detects the actual gender behind a mask, then we detect the landmark of the masked facial image. Second, we identified the non-face item, i.e., the mask, and used the Mask R-CNN network to create the binary mask of the observed mask area. Thirdly, we developed an inpainting network that uses anticipated landmarks to create realistic images. To segment the mask, this article uses a mask R-CNN and offers a binary segmentation map for identifying the mask area. Additionally, we generated the image utilizing landmarks as structural guidance through a GAN-based network. The studies presented in this paper use the FFHQ and CelebA datasets. This study outperformed all prior studies in terms of generating cutting-edge results for real-world pictures gathered from the web.
{"title":"A Deep Learning Framework to Reconstruct Face under Mask","authors":"Gourango Modak, S. Das, Md. Ajharul Islam Miraj, Md. Kishor Morol","doi":"10.1109/CDMA54072.2022.00038","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00038","url":null,"abstract":"While deep learning-based image reconstruction methods have shown significant success in removing objects from pictures, they have yet to achieve acceptable results for attributing consistency to gender, ethnicity, expression, and other characteristics like the topological structure of the face. The purpose of this work is to extract the mask region from a masked image and rebuild the area that has been detected. This problem is complex because (i) it is difficult to determine the gender of an image hidden behind a mask, which causes the network to become confused and reconstruct the male face as a female or vice versa; (ii) we may receive images from multiple angles, making it extremely difficult to maintain the actual shape, topological structure of the face and a natural image; and (iii) there are problems with various mask forms because, in some cases, the area of the mask cannot be anticipated precisely; certain parts of the mask remain on the face after completion. To solve this complex task, we split the problem into three phases: landmark detection, object detection for the targeted mask area, and inpainting the addressed mask region. To begin, to solve the first problem, we have used gender classification, which detects the actual gender behind a mask, then we detect the landmark of the masked facial image. Second, we identified the non-face item, i.e., the mask, and used the Mask R-CNN network to create the binary mask of the observed mask area. Thirdly, we developed an inpainting network that uses anticipated landmarks to create realistic images. To segment the mask, this article uses a mask R-CNN and offers a binary segmentation map for identifying the mask area. Additionally, we generated the image utilizing landmarks as structural guidance through a GAN-based network. The studies presented in this paper use the FFHQ and CelebA datasets. This study outperformed all prior studies in terms of generating cutting-edge results for real-world pictures gathered from the web.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128923919","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00029
Buşra Karatay, Deniz Bestepe, Kashfia Sailunaz, T. Ozyer, R. Alhajj
Emotion analysis is a subject that researchers from various fields have been working on for a long time. Different emotion detection methods have been developed for text, audio, photography, and video domains. Automated emotion detection methods using machine learning and deep learning models from videos and pictures have been an interesting topic for researchers. In this paper, a deep learning framework, in which CNN and Transformer models are combined, that classifies emotions using facial and body features extracted from videos is proposed. Facial and body features were extracted using OpenPose, and in the data preprocessing stage 2 operations such as new video creation and frame selection were tried. The experiments were conducted on two datasets, FABO and CK+. Our framework outperformed similar deep learning models with 99% classification accuracy for the FABO dataset, and showed remarkable performance over 90% accuracy for most versions of the framework for both the FABO and CK+ dataset.
{"title":"A Multi-Modal Emotion Recognition System Based on CNN-Transformer Deep Learning Technique","authors":"Buşra Karatay, Deniz Bestepe, Kashfia Sailunaz, T. Ozyer, R. Alhajj","doi":"10.1109/CDMA54072.2022.00029","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00029","url":null,"abstract":"Emotion analysis is a subject that researchers from various fields have been working on for a long time. Different emotion detection methods have been developed for text, audio, photography, and video domains. Automated emotion detection methods using machine learning and deep learning models from videos and pictures have been an interesting topic for researchers. In this paper, a deep learning framework, in which CNN and Transformer models are combined, that classifies emotions using facial and body features extracted from videos is proposed. Facial and body features were extracted using OpenPose, and in the data preprocessing stage 2 operations such as new video creation and frame selection were tried. The experiments were conducted on two datasets, FABO and CK+. Our framework outperformed similar deep learning models with 99% classification accuracy for the FABO dataset, and showed remarkable performance over 90% accuracy for most versions of the framework for both the FABO and CK+ dataset.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126137894","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00031
Amal Alazba, Leina Abouhagar, Randah Al-Harbi, Hamdi A. Al-Jamimi, Abdullah Sultan, Rabah A. Al-Zaidy
Discovering trends in research areas is helpful for researchers in finding the recent advances in a field or area of research. In addition, policy makers in universities can utilize this information in decision making. Different factors have direct influence on the growth and evolution of research topics. These include the funding, community interest and national needs. In this paper, we propose an unsupervised Dynamic Topic Modeling approach to discover and analyze the most trending research topics in a set of research areas using a collection of publications from the corresponding research areas. Furthermore, we study the correlation between emerging research trends and the different influencing factors.
{"title":"Detection of Research Trends using Dynamic Topic Modeling","authors":"Amal Alazba, Leina Abouhagar, Randah Al-Harbi, Hamdi A. Al-Jamimi, Abdullah Sultan, Rabah A. Al-Zaidy","doi":"10.1109/CDMA54072.2022.00031","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00031","url":null,"abstract":"Discovering trends in research areas is helpful for researchers in finding the recent advances in a field or area of research. In addition, policy makers in universities can utilize this information in decision making. Different factors have direct influence on the growth and evolution of research topics. These include the funding, community interest and national needs. In this paper, we propose an unsupervised Dynamic Topic Modeling approach to discover and analyze the most trending research topics in a set of research areas using a collection of publications from the corresponding research areas. Furthermore, we study the correlation between emerging research trends and the different influencing factors.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116047960","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 : 2022-03-01DOI: 10.1109/CDMA54072.2022.00008
Syed Abdul Rehman Khan, Muhammad Umar, M. Tanveer, Zhang Yu, L. Janjua
The Covid-19 pandemic has been assumed as a global pandemic as it caused disruption in all fields of life. The supply chain of manufacturing firms are also adversely affected by this pandemic. Keeping this in view, the current study is conducted to analyze the role of business data analytics (BDA) and digital marketing in improving Chinese firm performance during Covid-19. In this study, cross-sectional data was collected through questionnaire, and CB-SEM was employed to test hypotheses. The results indicate that BDA adoption helps firms move towards digital marketing and improve the firm's performance by effectively analyzing information, predicting behavioral model, and enhancing product delivery services. This article concluded that firms with well-developed technological infrastructure were least effected through Covid-19 pandemic. The current study recommends adopting BDA in firms as it helps firms respond to risky scenarios and enhances their resilience during uncertainty.
{"title":"Business Data Analytic and Digital Marketing: Business Strategies in the Era of COVID-19","authors":"Syed Abdul Rehman Khan, Muhammad Umar, M. Tanveer, Zhang Yu, L. Janjua","doi":"10.1109/CDMA54072.2022.00008","DOIUrl":"https://doi.org/10.1109/CDMA54072.2022.00008","url":null,"abstract":"The Covid-19 pandemic has been assumed as a global pandemic as it caused disruption in all fields of life. The supply chain of manufacturing firms are also adversely affected by this pandemic. Keeping this in view, the current study is conducted to analyze the role of business data analytics (BDA) and digital marketing in improving Chinese firm performance during Covid-19. In this study, cross-sectional data was collected through questionnaire, and CB-SEM was employed to test hypotheses. The results indicate that BDA adoption helps firms move towards digital marketing and improve the firm's performance by effectively analyzing information, predicting behavioral model, and enhancing product delivery services. This article concluded that firms with well-developed technological infrastructure were least effected through Covid-19 pandemic. The current study recommends adopting BDA in firms as it helps firms respond to risky scenarios and enhances their resilience during uncertainty.","PeriodicalId":313042,"journal":{"name":"2022 7th International Conference on Data Science and Machine Learning Applications (CDMA)","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121812814","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：