Table 6 Discipline classification labels and data distribution
From: HsscBERT: pre-training domain model for the full text of Chinese humanity and social science
Academic discipline | Number of studies | Effective documentation | Training set | Test set | Academic discipline | Number of studies | Effective documentation | Training set | Test set |
|---|---|---|---|---|---|---|---|---|---|
Science of law | 10,284 | 7192 | 1796 | 204 | Library, Information Science and Documentation | 6594 | 5274 | 1822 | 178 |
Management science | 13,513 | 8558 | 1814 | 186 | Foreign literature | 1749 | 1214 | 1103 | 111 |
Education science | 12,758 | 9199 | 1810 | 190 | Psychology | 2052 | 1832 | 1642 | 190 |
Economics (as a field of study) | 33,030 | 17,404 | 1803 | 197 | Journalism and Communication | 3800 | 1794 | 1624 | 170 |
Archaeology | 421 | 110 | 100 | 10 | Art Theory | 3869 | 1638 | 1471 | 167 |
Rare studies | 490 | 411 | 366 | 45 | Linguistics | 2523 | 1802 | 1621 | 181 |
History | 9311 | 5959 | 1795 | 205 | Philosophy | 7994 | 4239 | 1777 | 223 |
Marxist theory | 11,423 | 7038 | 1782 | 218 | Political Science | 13,901 | 9354 | 1799 | 201 |
Ethnography and cultural studies | 1632 | 1234 | 1091 | 143 | Chinese literature | 6068 | 2032 | 1805 | 195 |
Human and economic geography | 3074 | 2472 | 1782 | 218 | Natural Resources and Environmental Science | 950 | 714 | 645 | 69 |
Sociology | 3353 | 2013 | 1807 | 193 | Science of Religion | 560 | 409 | 377 | 32 |
Science of physical culture and sports | 2102 | 1779 | 1608 | 171 | Comprehensive journal sponsored by universities | 2790 | 2021 | 1795 | 205 |
Statistics | 1038 | 622 | 559 | 63 | Integrated social sciences | 37,241 | 24,811 | 1809 | 191 |
