对编辑的AI帮助。探索AI辅助文章分类系统的可能性
An AI aid to the editors. Exploring the possibility of an AI assisted article classification system
摘要：
这项工作是一个初步的探索性研究，我们如何能够取得进展的一步，人工智能辅助文章分类系统在学术界。拟议的系统旨在帮助期刊编辑在他们的决定，通过精确定位的潜在弱点或提交的手稿的优势。从大量的文章和相应的作者-编辑的互动，我们探讨了可能的原因，导致论文不被转发审查。我们的调查显示，在大多数情况下，这要么是因为预期的稿件超出了期刊的范围，要么是稿件不符合维持期刊标准的最低质量要求。我们提取了几个特征来量化论文的质量和范围内的探索性关键字搜索，引文分析，作者和从属关系的声誉，与公认的论文的相似性的程度。利用这些功能，我们训练标准的机器学习分类器来开发分类系统。在一组不错的测试数据上，我们的方法在3种不同的期刊上产生了有希望的结果。我们相信，我们的方法是通用的，可以适应其他期刊进行适当的调整。
英文摘要：
This work is a preliminary exploratory study of how we could progress a step towards an AI assisted article classification sys- tem in academia. The proposed system aims to aid the journal editors in their decisions by pinpointing the potential weaknesses or strengths of a submitted manuscript. From a large collection of articles and corresponding author-editor interactions we explore the possible reasons that lead to a paper being not forwarded for review. Our investigation reveals that in most cases either it is be- cause the prospective manuscript is out of scope of the journal or the manuscript does not satisfy the minimum quality requirements to maintain the standard of the journal. We extract several features to quantify the quality of a paper and the degree of in-scope explor- ing keyword search, citation analysis, reputations of authors and affiliations, similarity with respect to accepted papers. With these features we train standard machine learning classifiers to develop a classification system. On a decent set of test data our approach yields promising results across 3 different journals. We believe that our approach is generic and could be adapted to other journals with appropriate adjustments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
