grano1 commited on
Commit
638109b
·
verified ·
1 Parent(s): e1fe80b

extend readme for organizational card

Browse files
Files changed (1) hide show
  1. README.md +24 -7
README.md CHANGED
@@ -7,23 +7,40 @@ sdk: static
7
  pinned: false
8
  ---
9
 
10
- # Open Multi-Label ASJC Classification
11
 
12
  This Team Space hosts the **open, multi-label implementation of the All Science Journal Classification (ASJC) taxonomy**, designed to classify scientific documents at the individual level.
13
 
14
- ## Purpose
 
 
 
 
 
 
 
 
15
  Traditional ASJC classification is limited by incomplete sources, journal-level labels, and single-label assignments. This project provides:
16
  - **Multi-label classification across 307 subjects**
17
  - Fine-tuned **SciBERT model** trained on Crossref metadata
18
  - Methods for **collection-level analysis** (researcher portfolios, institutions, datasets)
19
 
20
- ## Features
21
- - High accuracy: F1-score 0.892 (307 subjects), 0.934 (26 parent subjects)
22
  - Works with or without source title metadata
23
  - Open, reproducible, and ready for research use
24
 
25
- ## Contents
26
- - Models, code, and notebooks for reproducing results
27
  - Example datasets and label-averaging utilities
28
 
29
- **Team:** Michael Gusenbauer, Jochen Endermann, Harald Huber, Simon Strasser, Andreas-Nizar Granitzer, Thomas Ströhle
 
 
 
 
 
 
 
 
 
 
7
  pinned: false
8
  ---
9
 
10
+ # 🧠 Open Multi-Label ASJC Classification
11
 
12
  This Team Space hosts the **open, multi-label implementation of the All Science Journal Classification (ASJC) taxonomy**, designed to classify scientific documents at the individual level.
13
 
14
+ ## 👥 Team
15
+ - **Michael Gusenbauer** – Johannes Kepler University Linz | ORCID: [https://orcid.org/0000-0001-7768-2351](https://orcid.org/0000-0001-7768-2351)
16
+ - **Jochen Endermann** – University of Applied Sciences Kufstein
17
+ - **Harald Huber** – University of Applied Sciences Kufstein
18
+ - **Simon Strasser** – University of Applied Sciences Kufstein
19
+ - **Andreas-Nizar Granitzer** – Norwegian Geotechnical Institute | ORCID: [https://orcid.org/0000-0002-5839-4300](https://orcid.org/0000-0002-5839-4300)
20
+ - **Thomas Ströhle** – Universität Innsbruck | ORCID: [https://orcid.org/0000-0002-1954-6412](https://orcid.org/0000-0002-1954-6412)
21
+
22
+ ## 🎯 Purpose
23
  Traditional ASJC classification is limited by incomplete sources, journal-level labels, and single-label assignments. This project provides:
24
  - **Multi-label classification across 307 subjects**
25
  - Fine-tuned **SciBERT model** trained on Crossref metadata
26
  - Methods for **collection-level analysis** (researcher portfolios, institutions, datasets)
27
 
28
+ ## Features
29
+ - High performance: weighted F1-score 0.892 (307 subjects) | 0.934 (26 parent subjects)
30
  - Works with or without source title metadata
31
  - Open, reproducible, and ready for research use
32
 
33
+ ## 🗂 Content
34
+ - Model and code for reproducing results
35
  - Example datasets and label-averaging utilities
36
 
37
+ ## 📖 Citation
38
+ If you use this work, please cite:
39
+
40
+ ```bibtex
41
+ @article{gusenbauer2025open,
42
+ author = {Gusenbauer, Michael and Endermann, Jochen and Huber, Harald and Strasser, Simon and Granitzer, Andreas-Nizar and Ströhle, Thomas},
43
+ title = {Open Multi-Label Implementation of the All Science Journal Classification (ASJC) Taxonomy},
44
+ journal = {Scientometrics},
45
+ year = {2025}
46
+ }