University of the Aegean

About: University of the Aegean is a education organization based out in Mytilene, Greece. It is known for research contribution in the topics: Population & Context (language use). The organization has 2818 authors who have published 8100 publications receiving 179275 citations. The organization is also known as: UAEG.

Measurement of charm and beauty production in deep inelastic ep scattering from decays into muons at HERA

Abstract: The production of charm and beauty quarks in ep interactions has been measured with the ZEUS detector at HERA for squared four-momentum exchange Q^2>20 GeV^2, using an integrated luminosity of 126 pb^{-1}. Charm and beauty quarks were identified through their decays into muons. Differential cross sections were measured for muon transverse momenta p_T^{\mu}>1.5 GeV and pseudorapidities -1.6<\eta^{\mu}<2.3, as a function of p_T^{\mu}, \eta^{\mu}, Q^2 and Bjorken x. The charm and beauty contributions to the proton structure function F_2 were also extracted. The results agree with previous measurements based on independent techniques and are well described by QCD predictions. Comment: 14 pages, 6 tables, 7 figures, accepted by EPJC

Sentiment Analysis of Figurative Language using a Word Sense Disambiguation Approach

Abstract: In this paper we propose a methodology for sentiment analysis of figurative language which applies Word Sense Disambiguation and, through an n-gram graph based method, assigns polarity to word senses. Polarity assigned to senses, combined with contextual valence shifters, is exploited for further assigning polarity to sentences, using Hidden Markov Models. Evaluation results using the corpus of the Aective Text task of SemEval’07, are presented together with a comparison with other state-of-the-art methods, showing that the proposed method provides promising results, and positive evidence supporting our conjecture: figurative language conveys sentiment.

Comparison of Different Classifiers for Emotion Recognition

Abstract: In the present paper a comparison of two classifiers for speech signal emotion recognition is presented. Recognition was performed on emotional Berlin Database. Within this work we concentrate on the evaluation of a speaker-dependent and speaker independent emotion recognition classification. One hundred thirty three (133) speech features obtained from speech signal processing. A basic set of 35 features was selected by statistical method and artificial neural network and Random Forest classifiers were used. Seven classes were categorized, namely anger, happiness, anxiety/fear, sadness, boredom, disgust and neutral. In speaker dependent framework, artificial neural network classification reached an accuracy of 83,17%, and Random Forest 77,19%. In speaker independent framework, for artificial neural network classification a mean accuracy of 55% was reached, while Random Forest reached a mean accuracy of 48%