BACKGROUND The risks associated with negative doctor-patient relationships have seriously hindered the healthy development of medical and healthcare and aroused wide-spread concern in society.The number of public comm...BACKGROUND The risks associated with negative doctor-patient relationships have seriously hindered the healthy development of medical and healthcare and aroused wide-spread concern in society.The number of public comments on doctor-patient relationship risk events reflects the degree to which the public pays attention to such events.Thirty incidents of doctor-patient disputes were collected from Weibo and TikTok,and 3655 related comments were extracted.The number of comment sentiment words was extracted,and the comment sentiment value was calculated.The Kruskal-Wallis H test was used to compare differences between each variable group at different levels of incidence.Spearman’s correlation analysis was used to examine associations between variables.Regression analysis was used to explore factors influencing scores of comments on incidents.RESULTS The study results showed that public comments on media reports of doctor-patient disputes at all levels are mainly dominated by“good”and“disgust”emotional states.There was a significant difference in the comment scores and the number of partial emotion words between comments on varying levels of severity of doctor-patient disputes.The comment score was positively correlated with the number of emotion words related to positive,good,and happy)and negatively correlated with the number of emotion words related to negative,anger,disgust,fear,and sadness.CONCLUSION The number of emotion words related to negative,anger,disgust,fear,and sadness directly influences comment scores,and the severity of the incident level indirectly influences comment scores.展开更多
Social media platforms like Instagram have increasingly become venues for online abuse and offensive comments. This study aimed to enhance user security to create a safe online environment by eliminating hate speech a...Social media platforms like Instagram have increasingly become venues for online abuse and offensive comments. This study aimed to enhance user security to create a safe online environment by eliminating hate speech and abusive language. The proposed system employed a multifaceted approach to comment filtering, incorporating the multi-level filter theory. This involved developing a comprehensive list of words representing various types of offensive language, from slang to explicit abuse. Machine learning models were trained to identify abusive messages through sentiment analysis and contextual understanding. The system categorized comments as positive, negative, or abusive using sentiment analysis algorithms. Employing AI technology, it created a dynamic filtering mechanism that adapted to evolving online language and abusive behavior. Integrated with Instagram while adhering to ethical data collection principles, the platform sought to promote a clean and positive user experience, encouraging users to focus on non-abusive communication. Our machine-learned models, trained on a cleaned Arabic language dataset, demonstrated promising accuracy (75.8%) in classifying Arabic comments, potentially reducing abusive content significantly. This advancement aimed to provide users with a clean and positive online experience.展开更多
随着新能源汽车市场占有份额不断增大,从相关用户评论中挖掘用户需求及分析情感倾向十分重要,然而该领域评论复杂多样,常用的分析方法难以实现多维度、深层次的数据挖掘,提炼其真实情感仍然存在着不小的难度及挑战。针对以上问题,提出...随着新能源汽车市场占有份额不断增大,从相关用户评论中挖掘用户需求及分析情感倾向十分重要,然而该领域评论复杂多样,常用的分析方法难以实现多维度、深层次的数据挖掘,提炼其真实情感仍然存在着不小的难度及挑战。针对以上问题,提出一种基于Transformer的双向编码(Bidirectional Encoder Representation from Transformers,BERT)和VADER规则的情感分析框架。该框架由BERT模型对用户评论情感倾向进行分类预测、VADER情感词库进行情感打分,并根据最终得分结果进行综合比较分析。该情感分析框架在爬取的“汽车之家”和“爱卡汽车网”的50520条用户评论数据集上表现出良好的情感分析效果,能准确识别用户情感并体现出不同新能源汽车品牌之间的区分度,可以为企业产品改进创新和用户选择产品时提供相关建议和参考价值。展开更多
基金Supported by the National Natural Science Foundation of China,No.72374005Natural Science Foundation for the Higher Education Institutions of Anhui Province of China,No.2023AH050561Cultivation Programme for Young and Middle-aged Excellent Teachers in Anhui Province,No.YQZD2023021.
文摘BACKGROUND The risks associated with negative doctor-patient relationships have seriously hindered the healthy development of medical and healthcare and aroused wide-spread concern in society.The number of public comments on doctor-patient relationship risk events reflects the degree to which the public pays attention to such events.Thirty incidents of doctor-patient disputes were collected from Weibo and TikTok,and 3655 related comments were extracted.The number of comment sentiment words was extracted,and the comment sentiment value was calculated.The Kruskal-Wallis H test was used to compare differences between each variable group at different levels of incidence.Spearman’s correlation analysis was used to examine associations between variables.Regression analysis was used to explore factors influencing scores of comments on incidents.RESULTS The study results showed that public comments on media reports of doctor-patient disputes at all levels are mainly dominated by“good”and“disgust”emotional states.There was a significant difference in the comment scores and the number of partial emotion words between comments on varying levels of severity of doctor-patient disputes.The comment score was positively correlated with the number of emotion words related to positive,good,and happy)and negatively correlated with the number of emotion words related to negative,anger,disgust,fear,and sadness.CONCLUSION The number of emotion words related to negative,anger,disgust,fear,and sadness directly influences comment scores,and the severity of the incident level indirectly influences comment scores.
文摘Social media platforms like Instagram have increasingly become venues for online abuse and offensive comments. This study aimed to enhance user security to create a safe online environment by eliminating hate speech and abusive language. The proposed system employed a multifaceted approach to comment filtering, incorporating the multi-level filter theory. This involved developing a comprehensive list of words representing various types of offensive language, from slang to explicit abuse. Machine learning models were trained to identify abusive messages through sentiment analysis and contextual understanding. The system categorized comments as positive, negative, or abusive using sentiment analysis algorithms. Employing AI technology, it created a dynamic filtering mechanism that adapted to evolving online language and abusive behavior. Integrated with Instagram while adhering to ethical data collection principles, the platform sought to promote a clean and positive user experience, encouraging users to focus on non-abusive communication. Our machine-learned models, trained on a cleaned Arabic language dataset, demonstrated promising accuracy (75.8%) in classifying Arabic comments, potentially reducing abusive content significantly. This advancement aimed to provide users with a clean and positive online experience.
文摘随着新能源汽车市场占有份额不断增大,从相关用户评论中挖掘用户需求及分析情感倾向十分重要,然而该领域评论复杂多样,常用的分析方法难以实现多维度、深层次的数据挖掘,提炼其真实情感仍然存在着不小的难度及挑战。针对以上问题,提出一种基于Transformer的双向编码(Bidirectional Encoder Representation from Transformers,BERT)和VADER规则的情感分析框架。该框架由BERT模型对用户评论情感倾向进行分类预测、VADER情感词库进行情感打分,并根据最终得分结果进行综合比较分析。该情感分析框架在爬取的“汽车之家”和“爱卡汽车网”的50520条用户评论数据集上表现出良好的情感分析效果,能准确识别用户情感并体现出不同新能源汽车品牌之间的区分度,可以为企业产品改进创新和用户选择产品时提供相关建议和参考价值。