attributes, and an extent, a maximal set of obje ts sharing the attributes.
A ontext relies on a set of obje ts a set of attributes and a relation K G, M Con ept Analysis (FCA) be ause it extra ts on epts organized into a latti e, Formal Con ept Analysis [6℄ is a lassi ation method allowing to build a whi h is interesting for the navigation into the wiki. In this se tion, we briey introdu e FCA. the animal has the orresponding attribute. ample of ontext about animals. There are ve attributes that des ribe animals. je ts are animals: bat, bird, at and sh. In the table, a ross in one ell indi ate attribute , means that has the attribute m ∈ M (g, m) ∈ I g m. between obje ts of attributes . Considering an obje t and an I ⊆ G × M g ∈ G on ept latti e where on epts are omposed of an intent, a maximal set of Animals may have hair, feather, wings. They might breath in air or water. Obmethod. A tually, any lassi ation methods might be used. We hoose Formal In this paper, we present a smart agent that enri h a wiki based on a lassi ation A ontext an be visualized as a binary table. Table 1 shows a (simple) exr e ir ta a w irah ftreeah isgn in in
e e w tah tah sa sa sa re re H H H B B
Fig. 1. Galois latti e based on the ontext from table 1 3.1 Prin iples this page has two semanti links isAbout:Networks and isTaughtBy:Prof. this page has two semanti links isAbout:Artifi ial Intelligen e and Intelligen e and isTaughtBy:Prof. Smith; has two semanti links isAbout:Networks and isTaughtBy:Prof. Jones; Design Patterns, in the Course and Master 1 Level ategories, this Knowledge Dis overy, in the Course and Master 1 Level ategories, Topi ategory; page has two semanti links isAbout:Artifi ial Intelligen e and Jones; Prof. Smith and Prof. Jones in the Professor ategory; IPv6 Proto ol, in the Course and Master 2 Level ategories, this page isTaughtBy:Prof. Smith; ategories, this page has two semanti links isAbout:Artifi ial page has two semanti links isAbout:Software Engineering and Semanti Web, in the Course, Master 1 Level and Master 2 Level isTaughtBy:Prof. Jones; isTaughtBy:Prof. Smith; Semanti Wiki, in the Course and Master 2 Level ategories, this Artifi ial Intelligen e, Software Engineering and Networks in the Network Administration, in the Course and Master 1 Level ategories, egories are identi al and should be merged (however this ase is very unlikely). Ea h ategory maps one (and only one) on ept: the most general on ept onA mapping between original ategories and latti e on epts is performed. taining the ategory in its intent (the attribute on ept). Ea h on ept maps If a on ept does not map any ategory, a new ategory will be reated. will be preserved. If a on ept maps two ategories or more, it means these atCurrently, the enri hment is performed by a Java appli ation that a ess the zero, one or several ategories. If a on ept maps a single ategory the ategory ontent of the wiki and reate an enri hed version of it. a ademi s. Here we present the initial ontent of the wiki. We have the following The method presented in this paper will be illustrated by a wiki on erning (user-dened) ategories:
3.2 Case study Finally, we added pages in the wiki:
Property:isAbout, the domain is a ourse, the range a topi . een irgn ig ee ith se lle ign
Sm oJn Itn n leev leev :froP :fro ila reaE rsok . .
P it ftw tw
L L y y r o e fssrreoo iop rseou leev stre1a srte2a taghuB taghuB :tobuA :tobuS :tobuN P T C L M M isT isT isA isA isA served in the enri hed wiki. This is the ase of the ategory Topi , for instan e.
If a on ept mat hes one and only one ategory, this ategory will simply be preA tually, in most ases, all the original ategories are preserved. merged by the FCA.
Category merging should be rare. It only happens if two or more ategories ea h pages are on atenated together. A default title is given to the ategory.
If a on ept mat hes two ategories or more, a new ategory is reated. This This is the ase of the two ategories Course and Level. Having these two ategory for this on ept. always appear in the exa t same pages. This would happen if several users use these dierent ategories will appear in all the same pages and then will be dierent terms for the same on ept. Bit by bit, after a number of wiki edition, new ategory will merge the ontent of the original mat hing ategories: text of ategories is due to a naming problem. The enri hed wiki has now only one
This might happens in two (non-ex lusive) ases: 3.7 Category enri hment 4 Validation
(Category:New Category 42, for instan e). As explained in previously, the new relevant ones, text should be rened. We will present three examples of validation. and update the hierar hal links onsequently. that and rename the merged ategory Course. They will also rename two of The last example on erns a sub ategory of Master 1 Course and Prof. not useful. A human user would de ide to remove this ategory from the wiki ategory about ourses taught by Prof. Jones. intelligible. users should edit all the ategories: default titles should be hanged into more merged. Having this two ategories was a mistake. Human users will a knowledge Another example on erns a new ategory that has been reated based The rst one on erns the two ategories Course and Level that have been merged ategories might be spit, some new ategories removed. Also, human on the semanti relation in the page Design Patterns with a default name ategory will ontain a text des ribing some properties of the on ept. A human Jones’ Course. One might onsider this ategory to be irrelevant, or at least the sub ategories Master 1 Course and Master 2 Course to make them more neering and will rename it onsequently. The same thing will be done for the user will understand that this ategory ontains ourses about software engi
tain the senten e The pages belonging to this ategory seems to have relation the ategory.
Property:isAbout with the page Software Engineering., as a des ription of For instan e, the ategory of ourses about software engineering will onwith new text ontent, based on properties. Senten es like The pages belonging to this ategory seems to have relation with the page . would be appended in T P the page. This will help human users to understand the meaning of the ategory.
Fig. 3. Man-ma hine ollaboration pro ess 4.2 Distributed wiki organization Category:Professor, ontains pages about Prof. Smith and Prof. Jones; pro ess of ontinuously knowledge building and orre t humans errors. of the wiki is ensured by the use of DSMW: a se ond wiki site is used to store Semanti wikis allow users to build knowledge understandable by humans and In this paper, we proposed a new smart agent based on Formal Con ept Analysis. This smart agent allows to reorganize the wiki: new ategories are new member of ommunities to produ e and maintain knowledge. Consequently, organization of the ontent and fa ilitate the navigation in the wiki. wiki pages as humans an do. This opens the opportunity to onsider ma hines as The refa toring pro ess needs to be validated by human users. Consisten y su h smart agents an redu e signi antly the overhead of ommunities in the omputed and pages are pla ed into these new ategories. This allows a better omputers. By this way, they also allow ma hines to produ e or update semanti
Category:Master 2 Artifi ial Intelligen e Course, a sub ategory Category:Master 2 Course, a sub ategory of Category:Course; Category:Master 2 Artifi ial Intelligen e Course, ontains the Software Engineering; Category:Prof. Jones’ Course and Category:Master 1 Course, Course, ontains the page about Knowledge Dis overy; Category:Prof. Jones’ Course, a sub ategory of Category:Course; Category:Master 1 and 2 Artifi ial Intelligen e Course, a subof Category:Master 1 Course and Category:Artifi ial Intelligen e Category:Master 2 Networks Course, a sub ategory of Category:Master the ourses in this ategory; ontains the page about Design Patterns; Category:Master 1 Networks Course, a sub ategory of Category:Master of Category:Master 2 Course and Category:Artifi ial Intelligen e page about Semanti Web; Category:Master 1 Artifi ial Intelligen e Course, a sub ategory ategory of Category:Master 1 Artifi ial Intelligen e Course and Category:Topi , ontains pages about Networks, Arti ial Intelligen e and Category:Artifi ial Intelligen e Course, a sub ategory of Category:Master 1 Course, a sub ategory of Category:Course; Category:Course, the page indi ates that Prof. Smith is tea hing all Category:Networks Course, a sub ategory of Category:Prof. Jones’ Category:Course; work Administration; Category:Software Engineering Course, a sub ategory of Proto ol. Course; 1 Course and Category:Networks Course, ontains the page about Net2 Course and Category:Networks Course, ontains the page about IPv6 the modi ation by human users during the validation pro ess. problem, the smart agent has to be history-aware and use the information of reated. However, the smart agent does not have a feedba k from the human large amount of on epts, and it would by impossible for human users to validate agent will reate it again when the pro ess will be reiterated. To avoid this riteria. any one of them. Some ltering methods should be used to prevent irrelevant future. Clearly, if applied on a real wiki, a method su h as FCA would produ e a ategories to be added, based on the number of instan es in a ategory or other In the urrent version of our method, human users have a feedba k from the Using Relational Con ept Analysis instead of FCA should provide interesting smart agent, they will take into onsideration the new ategories that have been validation. the result of the smart agent and is pulled ba k to the main wiki after human users: if a ategory has been reje ted during the validation pro ess, the smart This paper presented an early work, and more resear h have to be done in the results. Other lustering methods will also be onsidered.
Referen es