Stefan Trausan-Matu

Drexel E-Repository and Archive (iDEA) http://idea.library.drexel.edu/ ... Drexel University Libraries www.library.drexel.edu ... The following item is made available as a courtesy to scholars by the author(s) and Drexel University Library and may contain materials and content, including ...

Drexel E-Repository and Archive (iDEA) http://idea.library.drexel.edu/ ... Drexel University Libraries www.library.drexel.edu ... The following item is made available as a courtesy to scholars by the author(s) and Drexel University Library and may contain materials and content, including ...

ABSTRACT The paper presents a solution to the problem of capitalizing in different contexts and by different stakeholders the time-stamped new documents produced by social Web sites (including news, blog entries, and uploaded documents). The solution core includes an ontology-based method to express the interest topics and to automatically classify them. For such textual content obtained in real-time, we propose an unsupervised text classification system based on general YAGO ontology, graph algorithms and a custom scoring method. The system shows good performance using only ontology information and the ontology structure itself. We compare our system against a SVM-based (Support Vector Machine) classic text classification approach. For determining the relevance of a specific document for a specific topic, our approach develops and compares the ontology sub graphs corresponding to the query and to the document. It leads to a high flexibility in terms of capitalizing the already classified documents when refining and changing the interest topic: a graph-based matching of the already obtained ontology-based document representation against the new query representation is enough to assess the document relevance.

We investigated the influence of valence shifters on sentiment analysis within a new model built to extract opinions from economic texts. The system relies on implicit convictions that emerge from the studied texts through co-occurrences of economic indicators and future state modifiers. The polarity of the modifiers can however easily be reversed using negations, diminishers or intensifiers. We compared the system results with and without counting the effect of negations and future state modifier strength and we found that ...

Rezumat. Modelarea topicelor este o direcţie de cercetare în plină ascensiune care necesită noi metode de evaluare şi interpretare a rezultatelor. În această lucrare propunem o metodă pentru evaluarea şi îmbunătăţirea rezultatelor algoritmilor de extragere de topice bazândune pe concepte din WordNet. Propunem o metrică pentru determinarea calităţii unui model de topice plecând de la acoperirea sa şi redundanţa sa internă. Apoi, pentru fiecare topic, la nivel individual, cantitatea de informaţie relevantă pe care o aduce ...