Deriving Interests from Keywords
نویسنده
چکیده
Currently a new version of the distance education platform WeLearn [3] to be combined with an agent system ([1], also developed locally) for providing advanced services [2] is under development. In a previous stage of the project software was created to automatically derive keywords from documents, either from the different versions of metadata already contained (various Microsoft file formats, PDF, CPS-Manifests according to several specifications, HTML) or from plain text. The next stage is deriving a set of keywords with an associated interest measure for all persons (separately for each student by a personal agent). No ontology is used so the system remains universally applicable, but probably at the cost of slightly lower quality. Currently we are considering the approach of a rules-based system with some similarities to neural networks, which is applied to the notifications generated by the user's actions.
منابع مشابه
Deriving Context Specific Information on the Web
The Web is huge, unstructured and diverse in quality, which makes searching for information difficult. In practice, few of the documents returned by a search engine are valuable to a user. Which documents are valuable depends on the context of the query. Some adequate context information provided in addition to keywords can improve significantly search precision. In this paper we propose a fram...
متن کاملUser Modeling Based on Emergent Domain Semantics
In this paper we present an approach to user modeling based on the domain model that we generate automatically by resource (text) content processing and analysis of associated tags from a social annotation service. User’s interests are modeled by overlaying the domain model – via keywords extracted from resource’s (text) content, and tags assigned by the user or other (similar) users. The user ...
متن کاملDesigning a frame: rhetorical strategies of architects
We examine the rhetorical strategy of architects in widely available architectural texts, to identify what words are available for use in the cultural register. Our results show that these cultural register texts use distinct but related rhetorics; vocabularies of competency that are revealed through clusters of keywords and which capture institutional logics of business, profession and state. ...
متن کاملDERIVING THE EQUATION OF STATE FOR LIQUIDS AND EXTENSION OF THE PRINCIPLE OF CORRESPONDING STATES
A new simple model is introduced for a liquid and an equation of state is derived based on this model and the statistical mechanical calculations. This equation of state works well for the non-polar and slightly polar liquids. The important conclusion that may be deduced from this equation of state is that if the reduced variables of state are chosen and defined appropriately, then, the pri...
متن کاملKeyword Extraction Based on Implicit Feedback
To improve the results from search engines and make them more personalized for the user, we need to find out about the interests of a particular user. Many of the search personalization methods analyse documents visited by the user and from these documents infer the user’s interests. However, this approach is not accurate, because the user is rarely interested in the whole document; he might be...
متن کامل