Varshney Deepika, Vishwakarma Dinesh Kumar
Biometric Research Laboratory, Department of Information Technology, Delhi Technological University, Delhi, 110042 India.
Neural Comput Appl. 2023;35(8):5999-6013. doi: 10.1007/s00521-022-07938-3. Epub 2022 Nov 13.
Spreading of misleading information on social web platforms has fuelled huge panic and confusion among the public regarding the Corona disease, the detection of which is of paramount importance. To identify the credibility of the posted claim, we have analyzed possible evidence from the news articles in the google search results. This paper proposes an intelligent and expert strategy to gather important clues from the top 10 google search results related to the claim. The N-gram, Levenshtein Distance, and Word-Similarity-based features are used to identify the clues from the news article that can automatically warn users against spreading false news if no significant supportive clues are identified concerning that claim. The complete process is done in four steps, wherein the first step we build a query from the posted claim received in the form of text or text additive images which further goes as an input to the search query phase, where the top 10 google results are processed. In the third step, the important clues are extracted from titles of the top 10 news articles. Lastly, useful pieces of evidence are extracted from the content of each news article. All the useful clues with respect to N-gram, Levenshtein Distance, and Word Similarity are finally fed into the machine learning model for classification and to evaluate its performances. It has been observed that our proposed intelligent strategy gives promising experimental results and is quite effective in predicting misleading information. The proposed work provides practical implications for the policymakers and health practitioners that could be useful in protecting the world from misleading information proliferation during this pandemic.
社交网络平台上误导性信息的传播在公众中引发了对新冠疾病的巨大恐慌和混乱，而新冠疾病的检测至关重要。为了确定所发布声明的可信度，我们分析了谷歌搜索结果中新闻文章的可能证据。本文提出了一种智能且专业的策略，从与该声明相关的谷歌搜索结果前10名中收集重要线索。基于N-gram、莱文斯坦距离和词相似度的特征被用于从新闻文章中识别线索，如果未找到与该声明相关的重要支持线索，这些线索可以自动警告用户不要传播虚假新闻。整个过程分四个步骤完成，第一步，我们根据以文本或文本附加图像形式收到的所发布声明构建查询，该查询进一步作为搜索查询阶段的输入，在该阶段处理谷歌搜索结果前10名。第三步，从10篇新闻文章的标题中提取重要线索。最后，从每篇新闻文章的内容中提取有用的证据。所有关于N-gram、莱文斯坦距离和词相似度的有用线索最终被输入到机器学习模型中进行分类并评估其性能。据观察，我们提出的智能策略给出了有前景的实验结果，并且在预测误导性信息方面相当有效。所提出的工作为政策制定者和健康从业者提供了实际意义，这在保护世界免受本次大流行期间误导性信息扩散方面可能会有所帮助。
