Page 123 - JOURNAL OF LIBRARY SCIENCE IN CHINA 2015 Vol. 41

122 Journal of Library Science in China, Vol. 7, 2015

such as Event, Conference, Political party, Institution and Social group, meanwhile these classes
are linked to the Person class and other classes. By searching the ontology, it can be obtained that
“Mao Zedong” participated the “The First Plenary Session of the Central People’s Government
Committee”, and this conference was held in October 1, 1949. Similarly, all the historical activities
can be revealed.

)JTUPSJDBM BDUJWJUZ PG .BP ;FEPOH

+BO UP 'FC þ$MFBO VQ UIF IPVTF CFGPSF FOUFUBJO HVFTUÿ QSPQPTFS

.BS UIF 4FDPOE 1MFOBSZ 4FTTJPO PG UIF UI /BUJPOBM TQFBLFS
$POHSFTT PG UIF $PNNVOJTU 1BSUZ PG $IJOB
+VO UP 1SFQBSBUPSZ NFFUJOH PG UIF /FX 1PMJUJDBM TQFBLFS
$POTVMUBUJWF $POGFSFODF
4FQU UP 1MFOBSZ 4FTTJPO PG UIF $IJOFTF 1FPQMFýT TQFBLFS
1PMJUJDBM $POTVMUBUJWF $POGFSFODF
"GUFSOPPO PO 0DU 5IF GJSTU QMFOBSZ TFTTJPO PG UIF $FOUSBM 1FPQMFýT TQFBLFS
(PWFSONFOU $PNNJUUFF
QN PO 0DU 'PVOEJOH $FSFNPOZ SFMBUFE QFSTPO

0DU $IBJSNBO PG 1FPQMFýT 3FWPMVUJPOBSZ .JMJUBSZ BQQPJOUNFOU
$PNNJUUFF
%FD .BP ;FEPOH BOE ;IPV &OMBJ WJTJUFE UIF 4PWJFU SFMBUFE QFSTPO
UP .BS 6OJPO BOE IFME 4JOP 4PWJFU UBMLT

Figure 7. Example of a historical activity.

4 Conclusions

To realize the effective organization and utilization of the historical knowledge on contemporary China,
this paper proposed the “Mining down, Organizing up” method. It combines automatic text mining
and manual identification to extract important knowledge objects and facts from history text items,
and builds the contemporary Chinese historical ontology for semantic organization and knowledge
discovery. Based on the ontology, this method can be applied to implement some applications such
as historical knowledge visualization, retrieval, association, and reorganization. This study shows
that the “Mining down, Organizing up” method can realize fine-grained representation of historical
knowledge on contemporary China and innovative application of knowledge organization based on
historical knowledge objects. This method can be used as a kind of new knowledge representation and
organization methods in other domains. However, this study also has some limitations: 1) the accuracy
of the extraction of knowledge objects and relevant facts from text should be improved, especially
the identification and recommendation of relevant national history facts, which can further reduce the