Pub Date : 2024-04-30DOI: 10.1109/mis.2024.3374582
Mohammad Anas, Anam Saiyeda, Shahab Saquib Sohail, Erik Cambria, Amir Hussain
Recent advances in the context of deep learning have led to the development of generative artificial intelligence (AI) models which have shown remarkable performance in complex language understanding tasks. This study proposes an evaluation of traditional deep learning algorithms and generative AI models for sentiment analysis. Experimental results show that RoBERTa outperforms all models, including ChatGPT and Bard, suggesting that generative AI models are not yet able to capture the nuances and subtleties of sentiment in text. We provide valuable insights into the strengths and weaknesses of different models for sentiment analysis and offer guidance for researchers and practitioners in selecting suitable models for their tasks.
{"title":"Can Generative AI Models Extract Deeper Sentiments as Compared to Traditional Deep Learning Algorithms?","authors":"Mohammad Anas, Anam Saiyeda, Shahab Saquib Sohail, Erik Cambria, Amir Hussain","doi":"10.1109/mis.2024.3374582","DOIUrl":"https://doi.org/10.1109/mis.2024.3374582","url":null,"abstract":"Recent advances in the context of deep learning have led to the development of generative artificial intelligence (AI) models which have shown remarkable performance in complex language understanding tasks. This study proposes an evaluation of traditional deep learning algorithms and generative AI models for sentiment analysis. Experimental results show that RoBERTa outperforms all models, including ChatGPT and Bard, suggesting that generative AI models are not yet able to capture the nuances and subtleties of sentiment in text. We provide valuable insights into the strengths and weaknesses of different models for sentiment analysis and offer guidance for researchers and practitioners in selecting suitable models for their tasks.","PeriodicalId":13160,"journal":{"name":"IEEE Intelligent Systems","volume":"155 1","pages":""},"PeriodicalIF":6.4,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140835600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Group behavior prediction and evolution in social networks aims to accurately predict and model trends and patterns of group behavior through detailed analysis of massive user data, which is of great significance to the formulation of marketing strategies, user experience, and business strategies. Therefore, experts in various fields are actively exploring the potential of social network data to develop more accurate group behavior prediction and evolution models. This article provides an overview of these studies and explores the challenges and opportunities faced by group behavior prediction and evolution in social networks.
{"title":"Group Behavior Prediction and Evolution in Social Networks","authors":"Jingchao Wang, Xinyi Zhang, Weimin Li, Xiao Yu, Fangfang Liu, Qun Jin","doi":"10.1109/mis.2024.3366668","DOIUrl":"https://doi.org/10.1109/mis.2024.3366668","url":null,"abstract":"Group behavior prediction and evolution in social networks aims to accurately predict and model trends and patterns of group behavior through detailed analysis of massive user data, which is of great significance to the formulation of marketing strategies, user experience, and business strategies. Therefore, experts in various fields are actively exploring the potential of social network data to develop more accurate group behavior prediction and evolution models. This article provides an overview of these studies and explores the challenges and opportunities faced by group behavior prediction and evolution in social networks.","PeriodicalId":13160,"journal":{"name":"IEEE Intelligent Systems","volume":"4 1","pages":""},"PeriodicalIF":6.4,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140835639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-30DOI: 10.1109/mis.2024.3366648
Daniel E. O’Leary
This article investigates how large language systems and the apps developed for them provide a platform for enterprise knowledge management. For those resulting systems to provide consistent and accurate responses for knowledge management, enterprises are using different approaches in their prompts, such as few-shot learning, specification of purpose, and chain-of-thought reasoning. As better and more successful prompts are being built, they are being captured and prompt libraries are being created.
{"title":"Large Language Models and Applications: The Rebirth of Enterprise Knowledge Management and the Rise of Prompt Libraries","authors":"Daniel E. O’Leary","doi":"10.1109/mis.2024.3366648","DOIUrl":"https://doi.org/10.1109/mis.2024.3366648","url":null,"abstract":"This article investigates how large language systems and the apps developed for them provide a platform for enterprise knowledge management. For those resulting systems to provide consistent and accurate responses for knowledge management, enterprises are using different approaches in their prompts, such as few-shot learning, specification of purpose, and chain-of-thought reasoning. As better and more successful prompts are being built, they are being captured and prompt libraries are being created.","PeriodicalId":13160,"journal":{"name":"IEEE Intelligent Systems","volume":"16 1","pages":""},"PeriodicalIF":6.4,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140835633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-30DOI: 10.1109/mis.2024.3380239
{"title":"IEEE Computer Society Career Center","authors":"","doi":"10.1109/mis.2024.3380239","DOIUrl":"https://doi.org/10.1109/mis.2024.3380239","url":null,"abstract":"","PeriodicalId":13160,"journal":{"name":"IEEE Intelligent Systems","volume":"9 1","pages":""},"PeriodicalIF":6.4,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140835536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-30DOI: 10.1109/mis.2024.3382792
{"title":"IEEE Computer Society Has You Covered!","authors":"","doi":"10.1109/mis.2024.3382792","DOIUrl":"https://doi.org/10.1109/mis.2024.3382792","url":null,"abstract":"","PeriodicalId":13160,"journal":{"name":"IEEE Intelligent Systems","volume":"36 1","pages":""},"PeriodicalIF":6.4,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140835581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-30DOI: 10.1109/mis.2024.3383098
{"title":"Get Published in the New IEEE Transactions on Privacy","authors":"","doi":"10.1109/mis.2024.3383098","DOIUrl":"https://doi.org/10.1109/mis.2024.3383098","url":null,"abstract":"","PeriodicalId":13160,"journal":{"name":"IEEE Intelligent Systems","volume":"74 1","pages":""},"PeriodicalIF":6.4,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140835635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：