Back to Search
Start Over
Large Scale Subject Category Classification of Scholarly Papers With Deep Attentive Neural Networks
- Source :
- Frontiers in Research Metrics and Analytics, Frontiers in Research Metrics and Analytics, Vol 5 (2021)
- Publication Year :
- 2021
- Publisher :
- Frontiers Media S.A., 2021.
-
Abstract
- Subject categories of scholarly papers generally refer to the knowledge domain(s) to which the papers belong, examples being computer science or physics. Subject category information can be used for building faceted search for digital library search engines. This can significantly assist users in narrowing down their search space of relevant documents. Unfortunately, many academic papers do not have such information as part of their metadata. Existing methods for solving this task usually focus on unsupervised learning that often relies on citation networks. However, a complete list of papers citing the current paper may not be readily available. In particular, new papers that have few or no citations cannot be classified using such methods. Here, we propose a deep attentive neural network (DANN) that classifies scholarly papers using only their abstracts. The network is trained using 9 million abstracts from Web of Science (WoS). We also use the WoS schema that covers 104 subject categories. The proposed network consists of two bi-directional recurrent neural networks followed by an attention layer. We compare our model against baselines by varying the architecture and text representation. Our best model achieves micro-F1 measure of 0.76 with F1 of individual subject categories ranging from 0.50-0.95. The results showed the importance of retraining word embedding models to maximize the vocabulary overlap and the effectiveness of the attention mechanism. The combination of word vectors with TFIDF outperforms character and sentence level embedding models. We discuss imbalanced samples and overlapping categories and suggest possible strategies for mitigation. We also determine the subject category distribution in CiteSeerX by classifying a random sample of one million academic papers.<br />Comment: submitted to "Frontiers Mining Scientific Papers Volume II: Knowledge Discovery and Data Exploitation"
- Subjects :
- FOS: Computer and information sciences
Vocabulary
Word embedding
text classification
media_common.quotation_subject
02 engineering and technology
text mining
scientific papers
Bibliography. Library science. Information resources
citeseerx
Research Metrics and Analytics
0202 electrical engineering, electronic engineering, information engineering
Digital Libraries (cs.DL)
digital library
tf–idf
media_common
Original Research
subject category classification
Computer Science - Computation and Language
Information retrieval
05 social sciences
Computer Science - Digital Libraries
Subject (documents)
General Medicine
Digital library
neural networks
Domain knowledge
Unsupervised learning
020201 artificial intelligence & image processing
0509 other social sciences
050904 information & library sciences
Computation and Language (cs.CL)
Sentence
Subjects
Details
- Language :
- English
- ISSN :
- 25040537
- Volume :
- 5
- Database :
- OpenAIRE
- Journal :
- Frontiers in Research Metrics and Analytics
- Accession number :
- edsair.doi.dedup.....39ca8252e411b42a5ae9f0a0c8656921