AI model predicts research paper quality using text analysis

Researchers have developed a method to classify scientific papers as high-quality or flawed using only textual features from their titles and abstracts. The study evaluated various embedding techniques and classifiers, finding that a neural network with SBERT embeddings achieved 87.22% accuracy, while a FastText-SVM combination reached 91.12%. This work aims to contribute to academic integrity tools by leveraging text analysis to promote trustworthy scholarship. AI

IMPACT This research could lead to automated tools that help identify high-quality or flawed scientific papers, improving academic integrity.

RANK_REASON The cluster describes a research paper detailing a new method for classifying research paper quality using textual features. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• arXiv
• FastText
• Hugging Face
• Neural Networks
• Random Forests
• SBERT
• TF-IDF
• USE
• Word2Vec

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →