Petar Branislav Jelušić, A. Poljicak, D. Donevski, T. Cigula
As sharing digital media is getting more prominent, there has been a rise in the development of techniques for protecting digital media against misuse. However, the amount of such techniques has been less prominent for printed goods. The data hiding method presented in this paper is suited for the print domain. The method uses the Discrete Fourier Transform to embed data into images and Gray Component Replacement to maintain high image quality by masking embedding artifacts. This research examines whether the method's performance can be optimized using low-frequency ranges for embedding. The aim is to evaluate the usage of low-frequency ranges in order to achieve higher robustness. Different frequency ranges are tested to determine how they affect image quality and detection rates. Tests are conducted in the digital domain. The results show that the method can maintain image quality regardless of the frequency range, and that low-frequency ranges lead to more consistent detection rates. Future research will be done on images in the print domain.
{"title":"Low-Frequency Data Embedding for DFT-Based Image Steganography","authors":"Petar Branislav Jelušić, A. Poljicak, D. Donevski, T. Cigula","doi":"10.4018/ijssci.312558","DOIUrl":"https://doi.org/10.4018/ijssci.312558","url":null,"abstract":"As sharing digital media is getting more prominent, there has been a rise in the development of techniques for protecting digital media against misuse. However, the amount of such techniques has been less prominent for printed goods. The data hiding method presented in this paper is suited for the print domain. The method uses the Discrete Fourier Transform to embed data into images and Gray Component Replacement to maintain high image quality by masking embedding artifacts. This research examines whether the method's performance can be optimized using low-frequency ranges for embedding. The aim is to evaluate the usage of low-frequency ranges in order to achieve higher robustness. Different frequency ranges are tested to determine how they affect image quality and detection rates. Tests are conducted in the digital domain. The results show that the method can maintain image quality regardless of the frequency range, and that low-frequency ranges lead to more consistent detection rates. Future research will be done on images in the print domain.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116722637","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}
While many eHealth innovation projects have emerged in the last few years, most of them remain as pilot projects. The purpose of this study is to improve our understanding of what conditions prevent these projects from not being implemented. Using a qualitative methodology, based on case studies, the authors studied projects that have been implemented and others that have remained pilots to compare what factors determine the real implementation. Four conditions emerge from the analysis that seem to have a great influence on their implementation: technological anxiety, facilities (specifically changes in developments), training, and social influence, particularly when training is given by health professionals who are part of the pilot project to other colleagues. This work highlights a set of actions that should be implemented in eHealth innovation projects and also provides a basis for defining strategies to reduce the risk of increasing the phenomenon of plague of pilot, increasing the success rate in the implementation of the projects.
{"title":"Factors Determining the Success of eHealth Innovation Projects","authors":"A. Hidalgo, Nerea Perez, Isaac Lemus-Aguilar","doi":"10.4018/ijssci.309709","DOIUrl":"https://doi.org/10.4018/ijssci.309709","url":null,"abstract":"While many eHealth innovation projects have emerged in the last few years, most of them remain as pilot projects. The purpose of this study is to improve our understanding of what conditions prevent these projects from not being implemented. Using a qualitative methodology, based on case studies, the authors studied projects that have been implemented and others that have remained pilots to compare what factors determine the real implementation. Four conditions emerge from the analysis that seem to have a great influence on their implementation: technological anxiety, facilities (specifically changes in developments), training, and social influence, particularly when training is given by health professionals who are part of the pilot project to other colleagues. This work highlights a set of actions that should be implemented in eHealth innovation projects and also provides a basis for defining strategies to reduce the risk of increasing the phenomenon of plague of pilot, increasing the success rate in the implementation of the projects.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"180 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127587913","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}
Blended learning has gained wide popularity, but its superiority is limited by insufficient connection between online and offline learning due to technological anxiety and complexity, which hampers the achievement of prospective learning effect. To shatter these limits, a smart learning assistant based on Wechat Mini Program is proposed that incorporates a score ranking mechanism based on explainable machine learning to improve learning interests in programming, a learning material recommendation with deep neural networks to solve the student's confusion in personalized learning source selection, and a learning review mechanism based on deep learning achievements to enhance teacher-student communication and student-student cooperation in learning. In addition, approximately 3200 learners are involved to investigate learning requirements and test system performance. The experimental and practical results demonstrate the superiority of the smart learning assistant and the effectiveness gained by promoting learning outcomes in blended learning.
{"title":"A Smart Learning Assistant to Promote Learning Outcomes in a Programming Course","authors":"Xiaotong Jiao, X. Yu, Haowei Peng, Xue Zhang","doi":"10.4018/ijssci.312557","DOIUrl":"https://doi.org/10.4018/ijssci.312557","url":null,"abstract":"Blended learning has gained wide popularity, but its superiority is limited by insufficient connection between online and offline learning due to technological anxiety and complexity, which hampers the achievement of prospective learning effect. To shatter these limits, a smart learning assistant based on Wechat Mini Program is proposed that incorporates a score ranking mechanism based on explainable machine learning to improve learning interests in programming, a learning material recommendation with deep neural networks to solve the student's confusion in personalized learning source selection, and a learning review mechanism based on deep learning achievements to enhance teacher-student communication and student-student cooperation in learning. In addition, approximately 3200 learners are involved to investigate learning requirements and test system performance. The experimental and practical results demonstrate the superiority of the smart learning assistant and the effectiveness gained by promoting learning outcomes in blended learning.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126135921","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}
Yuquan Fan, Xianglin Cao, Hong Xiao, Weilin Zhou, Wenchao Jiang
At present, the excessive amount of loan consultation has brought great pressure to manual customer service. However, the existing loan question answering (QA) platforms cannot solve this problem well because of their poor understanding ability. Therefore, the authors constructs a loan QA platform based on ERNIE and knowledge graph (KG). Firstly, they use semi-automatic methods to construct KG with data from a loan company. Secondly, they use token-level random mask strategy (TRM), word-level fixed mask strategy (WFM), and fine-tuning strategy integrating knowledge (IK) to train ERNIE. Finally, they construct a QA platform based on KG and trained ERNIE and experiment with proprietary datasets. The results show that ERNIE trained after three strategies achieve average improvements of 14.7% on judging intention similarity of sentence pairs and 14.28% on retrieving the most similar intention problem compared with the baseline. It also shows that their platform achieves an average improvement of 13% on question answering compared with the customer service app of the loan company.
{"title":"Loan Question Answering Platform Based on ERNIE and Knowledge Graph","authors":"Yuquan Fan, Xianglin Cao, Hong Xiao, Weilin Zhou, Wenchao Jiang","doi":"10.4018/ijssci.309427","DOIUrl":"https://doi.org/10.4018/ijssci.309427","url":null,"abstract":"At present, the excessive amount of loan consultation has brought great pressure to manual customer service. However, the existing loan question answering (QA) platforms cannot solve this problem well because of their poor understanding ability. Therefore, the authors constructs a loan QA platform based on ERNIE and knowledge graph (KG). Firstly, they use semi-automatic methods to construct KG with data from a loan company. Secondly, they use token-level random mask strategy (TRM), word-level fixed mask strategy (WFM), and fine-tuning strategy integrating knowledge (IK) to train ERNIE. Finally, they construct a QA platform based on KG and trained ERNIE and experiment with proprietary datasets. The results show that ERNIE trained after three strategies achieve average improvements of 14.7% on judging intention similarity of sentence pairs and 14.28% on retrieving the most similar intention problem compared with the baseline. It also shows that their platform achieves an average improvement of 13% on question answering compared with the customer service app of the loan company.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131967642","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}
The sudden outbreak of COVID-19 has dealt a huge blow to traditional education and training companies. Institutions use the WeChat platform to attract users, but how to identify high-quality users has always been a difficult point for enterprises. In this paper, researchers proposed a classification algorithm based on SMOTE and the improved AdaBoost, which fuses feature information weights and sample weights to effectively solve the problems of overfitting and sample imbalance. To justify the study, it was compared with other traditional machine-learning algorithms. The accuracy and recall of the model increased by 19% and 36%, respectively, and the AUC value reached 0.98, indicating that the model could effectively identify the user's purchase intention. The proposed algorithm also ensures that it works well in spam identification and fraud detection. This research is of great significance for educational institutions to identify high-quality users of the WeChat platform and increase purchase conversion rate.
{"title":"User Consumption Behavior Recognition Based on SMOTE and Improved AdaBoost","authors":"Huijuan Hu, Dingju Zhu, Tao Wang, Chao He, Juel Sikder, Yangchun Jia","doi":"10.4018/ijssci.315302","DOIUrl":"https://doi.org/10.4018/ijssci.315302","url":null,"abstract":"The sudden outbreak of COVID-19 has dealt a huge blow to traditional education and training companies. Institutions use the WeChat platform to attract users, but how to identify high-quality users has always been a difficult point for enterprises. In this paper, researchers proposed a classification algorithm based on SMOTE and the improved AdaBoost, which fuses feature information weights and sample weights to effectively solve the problems of overfitting and sample imbalance. To justify the study, it was compared with other traditional machine-learning algorithms. The accuracy and recall of the model increased by 19% and 36%, respectively, and the AUC value reached 0.98, indicating that the model could effectively identify the user's purchase intention. The proposed algorithm also ensures that it works well in spam identification and fraud detection. This research is of great significance for educational institutions to identify high-quality users of the WeChat platform and increase purchase conversion rate.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116826687","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}
Wenkai Niu, Juxiang Zhou, Jiabeizi He, Jianhou Gan
With the gradual application of facial expression recognition (FER) technology in various fields, the facial expression datasets based on specific scenes have gradually increased, effectively improving the application effect. However, the facial images of students collected in real classroom scenes often have problems, such as front and rear occlusion, blurred images, and small targets. Moreover, the current students' classroom expression recognition technology faces several challenges as a result of sample uncertainties. Therefore, this paper proposes an optimization algorithm for the uncertainties based on SCN. The correction weight of the sample through the sample weight was calculated, and the loss function was designed according to the correction weight. The dynamic threshold is obtained by combining the threshold in the noise relabeling module and the correction weight. The experimental results on public datasets and self-built classroom expression dataset show that the optimization algorithm effectively improves the robustness of SCN to uncertain samples.
{"title":"An Optimization Algorithm for the Uncertainties of Classroom Expression Recognition Based on SCN","authors":"Wenkai Niu, Juxiang Zhou, Jiabeizi He, Jianhou Gan","doi":"10.4018/ijssci.315653","DOIUrl":"https://doi.org/10.4018/ijssci.315653","url":null,"abstract":"With the gradual application of facial expression recognition (FER) technology in various fields, the facial expression datasets based on specific scenes have gradually increased, effectively improving the application effect. However, the facial images of students collected in real classroom scenes often have problems, such as front and rear occlusion, blurred images, and small targets. Moreover, the current students' classroom expression recognition technology faces several challenges as a result of sample uncertainties. Therefore, this paper proposes an optimization algorithm for the uncertainties based on SCN. The correction weight of the sample through the sample weight was calculated, and the loss function was designed according to the correction weight. The dynamic threshold is obtained by combining the threshold in the noise relabeling module and the correction weight. The experimental results on public datasets and self-built classroom expression dataset show that the optimization algorithm effectively improves the robustness of SCN to uncertain samples.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127289231","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}
According to the ubiquitous computing paradigm, dispersed computers within the home environment can support the residents’ health by being aware of all the developing and evolving situations. The context-awareness of the supporting computers stems from the data acquisition of the occurring events at home. In some cases, different sensors provide input of identical type, thereby raising conflict-related issues. Thus, for each type of input data, fusion methods must be applied on the raw data to obtain a dominant input value. Also, for diagnostic inference purpose, data fusion methods must be applied on the values of the available classes of multiple contextual data structures. Dempster-Shafer theory offers the algorithmic tools to efficiently fuse the data of each input type or class. The employment of threading technology accelerates the computational process and carrying out benchmarks on publicly available data set, is shown to be more efficient. Thus, threading technology proved promising for home UbiHealth applications by lowering the number of required cooperating computers.
{"title":"Fused Contextual Data With Threading Technology to Accelerate Processing in Home UbiHealth","authors":"J. Sarivougioukas, Aristides Vagelatos","doi":"10.4018/ijssci.285590","DOIUrl":"https://doi.org/10.4018/ijssci.285590","url":null,"abstract":"According to the ubiquitous computing paradigm, dispersed computers within the home environment can support the residents’ health by being aware of all the developing and evolving situations. The context-awareness of the supporting computers stems from the data acquisition of the occurring events at home. In some cases, different sensors provide input of identical type, thereby raising conflict-related issues. Thus, for each type of input data, fusion methods must be applied on the raw data to obtain a dominant input value. Also, for diagnostic inference purpose, data fusion methods must be applied on the values of the available classes of multiple contextual data structures. Dempster-Shafer theory offers the algorithmic tools to efficiently fuse the data of each input type or class. The employment of threading technology accelerates the computational process and carrying out benchmarks on publicly available data set, is shown to be more efficient. Thus, threading technology proved promising for home UbiHealth applications by lowering the number of required cooperating computers.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128915871","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}
Narina Thakur, Sunil K. Singh, Akash Gupta, Kunal Jain, Rachna Jain, D. Peraković, N. Nedjah, M. Rafsanjani
Human activity recognition (HAR) is a crucial and challenging classification task for a range of applications from surveillance to assistance. Existing sensor-based HAR systems have limited training data availability and lack fast and accurate methods for robust and rapid activity recognition. In this paper, a novel hybrid HAR technique based on CNN, bi-directional long short-term memory, and gated recurrent units is proposed that can accurately and quickly recognize new human activities with a limited training set and high accuracy. The experiment was conducted on UCI Machine Learning Repository's MHEALTH dataset to analyze the effectiveness of the proposed method. The confusion matrix and accuracy score are utilized to gauge the performance of the presented model. Experiments indicate that the proposed hybrid approach for human activity recognition integrating CNN, bi-directional LSTM, and gated recurrent outperforms computing complexity and efficiency. The overall findings demonstrate that the proposed hybrid model performs exceptionally well, with enhanced accuracy of 94.68%.
{"title":"A Novel CNN, Bidirectional Long-Short Term Memory, and Gated Recurrent Unit-Based Hybrid Approach for Human Activity Recognition","authors":"Narina Thakur, Sunil K. Singh, Akash Gupta, Kunal Jain, Rachna Jain, D. Peraković, N. Nedjah, M. Rafsanjani","doi":"10.4018/ijssci.311445","DOIUrl":"https://doi.org/10.4018/ijssci.311445","url":null,"abstract":"Human activity recognition (HAR) is a crucial and challenging classification task for a range of applications from surveillance to assistance. Existing sensor-based HAR systems have limited training data availability and lack fast and accurate methods for robust and rapid activity recognition. In this paper, a novel hybrid HAR technique based on CNN, bi-directional long short-term memory, and gated recurrent units is proposed that can accurately and quickly recognize new human activities with a limited training set and high accuracy. The experiment was conducted on UCI Machine Learning Repository's MHEALTH dataset to analyze the effectiveness of the proposed method. The confusion matrix and accuracy score are utilized to gauge the performance of the presented model. Experiments indicate that the proposed hybrid approach for human activity recognition integrating CNN, bi-directional LSTM, and gated recurrent outperforms computing complexity and efficiency. The overall findings demonstrate that the proposed hybrid model performs exceptionally well, with enhanced accuracy of 94.68%.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124351636","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}
Sabri Mohammed, Menaouer Brahami, Abid Faten Fatima Zohra, M. Nada
In today’s digital era, Twitter’s data has been the focus point among researchers as it provides specific data and in a wide variety of fields. Furthermore, Twitter’s daily usage has surged throughout the coronavirus disease (Covid-19) period, presenting a unique opportunity to analyze the content and sentiment of covid-19 tweets. In this paper, a new approach is proposed for the automatic sentiment classification of Covid-19 tweets using the Adaptive Neuro-Fuzzy Inference System (ANFIS) models. The entire process includes data collection, pre-processing, word embedding, sentiment analysis, and classification. Many experiments were accomplished to prove the validity and efficiency of the approach using datasets Covid-19 tweets and it accomplished the data reduction process to achieve considerable size reduction with the preservation of significant dataset's attributes. Our experimental results indicate that fuzzy deep learning achieves the best accuracy (i.e. 0.916) with word embeddings.
{"title":"Sentiment Analysis of COVID-19 Tweets Using Adaptive Neuro-Fuzzy Inference System Models","authors":"Sabri Mohammed, Menaouer Brahami, Abid Faten Fatima Zohra, M. Nada","doi":"10.4018/ijssci.300361","DOIUrl":"https://doi.org/10.4018/ijssci.300361","url":null,"abstract":"In today’s digital era, Twitter’s data has been the focus point among researchers as it provides specific data and in a wide variety of fields. Furthermore, Twitter’s daily usage has surged throughout the coronavirus disease (Covid-19) period, presenting a unique opportunity to analyze the content and sentiment of covid-19 tweets. In this paper, a new approach is proposed for the automatic sentiment classification of Covid-19 tweets using the Adaptive Neuro-Fuzzy Inference System (ANFIS) models. The entire process includes data collection, pre-processing, word embedding, sentiment analysis, and classification. Many experiments were accomplished to prove the validity and efficiency of the approach using datasets Covid-19 tweets and it accomplished the data reduction process to achieve considerable size reduction with the preservation of significant dataset's attributes. Our experimental results indicate that fuzzy deep learning achieves the best accuracy (i.e. 0.916) with word embeddings.","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132090508","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}
K. Pareek, Arjun Choudhary, A. Tripathi, K. Mishra, Namita Mittal
In today’s time, everyone is familiar with social media platforms. It is quite helpful in connecting people. It has many advantages and some disadvantages too. Currently, in social media, hate and aggression have become a huge problem. On these platforms, many people make inflammatory posts targeting any person or society by using code mixed language, due to which many problems arise in the society. At the current time, much research work is being done on English language-related social media posts. The authors have focused on code mixed language. Authors have also tried to focus on sentences that do not use abusive words but contain hatred-related remarks. In this research, authors have used Natural Language Processing (NLP). Authors have applied Fasttext word embedding to the dataset. Fasttext is a technique of NLP. Deep learning (DL) classification algorithms were applied thereafter. In this research, two classifications have been used i.e. Convolutional Neural Network (CNN) and Bidirectional LSTM (Bi-LSTM).
{"title":"Hate and Aggression Detection in Social Media Over Hindi English Language","authors":"K. Pareek, Arjun Choudhary, A. Tripathi, K. Mishra, Namita Mittal","doi":"10.4018/ijssci.300357","DOIUrl":"https://doi.org/10.4018/ijssci.300357","url":null,"abstract":"In today’s time, everyone is familiar with social media platforms. It is quite helpful in connecting people. It has many advantages and some disadvantages too. Currently, in social media, hate and aggression have become a huge problem. On these platforms, many people make inflammatory posts targeting any person or society by using code mixed language, due to which many problems arise in the society. At the current time, much research work is being done on English language-related social media posts. The authors have focused on code mixed language. Authors have also tried to focus on sentences that do not use abusive words but contain hatred-related remarks. In this research, authors have used Natural Language Processing (NLP). Authors have applied Fasttext word embedding to the dataset. Fasttext is a technique of NLP. Deep learning (DL) classification algorithms were applied thereafter. In this research, two classifications have been used i.e. Convolutional Neural Network (CNN) and Bidirectional LSTM (Bi-LSTM).","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131392771","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：