Detail publikace

Optimization Methods in Emotion Recognition System

POVODA, L. BURGET, R. MAŠEK, J. UHER, V. DUTTA, M.

Originální název

Optimization Methods in Emotion Recognition System

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

Emotions play big role in our everyday communication and contain important information. This work describes a novel method of automatic emotion recognition from textual data. The method is based on well-known data mining techniques, novel approach based on parallel run of SVM (Support Vector Machine) classifiers, text preprocessing and 3 optimization methods: sequential elimination of attributes, parameter optimization based on token groups, and method of extending train data sets during practical testing and production release final tuning. We outperformed current state of the art methods and the results were validated on bigger data sets (3346 manually labelled samples) which is less prone to overfitting when compared to related works. The accuracy achieved in this work is 86.89%for recognition of 5 emotional classes. The experiments were performed in the real world helpdesk environment, was processing Czech language but the proposed methodology is general and can be applied to many different languages.

Klíčová slova

Czech; Emotion classification; Emotion detection; Emotion recognition; Text mining

Autoři

POVODA, L.; BURGET, R.; MAŠEK, J.; UHER, V.; DUTTA, M.

Vydáno

3. 9. 2016

ISSN

1805-9600

Periodikum

Radioengineering

Ročník

25

Číslo

3

Stát

Česká republika

Strany od

565

Strany do

572

Strany počet

8

BibTex

@article{BUT127072,
  author="Lukáš {Povoda} and Radim {Burget} and Jan {Mašek} and Václav {Uher} and Malay Kishore {Dutta}",
  title="Optimization Methods in Emotion Recognition System",
  journal="Radioengineering",
  year="2016",
  volume="25",
  number="3",
  pages="565--572",
  doi="10.13164/re.2016.0565",
  issn="1805-9600"
}