Multi-class sentiment analysis using a hierarchical logistic model tree approach

Journal Title: MASKANA - Year 2014, Vol 5, Issue 5

Abstract

This paper proposes a new hybrid system for multi-class sentiment analysis based on General Inquirer (GI) dictionary and a hierarchical Logistic Model Tree (LMT) approach. This new system consists of three layers, the Bipolar Layer (BL) is of one LMT (LMT-1) for classifying sentiment polarity, while the Intensity Layer (IL) comprises two LTMs (LMT-2 and LMT3) for detecting separately three positive and three negative sentiment intensities. Only in construction phase, the Grouping Layer (GL) is used to cluster positive and negative instances by employing 2 k-means respectively. In Preprocessing phase, the raw text data is subjected to a tokenizer, a tagger, a stemmer and finally to GI dictionary to count and label only verbs, nouns, adjectives and adverbs with 24 markers that are used later to compute feature vectors. In Sentiments Classification phase, feature vectors are first introduced to LMT-1, then they are grouped in GL according to class label, afterward these groups of instances are labeled manually, and finally positive instances are introduced to LMT-2 and negative instances to LMT-3. The three trees are trained and tested on Movie Review and SenTube datasets utilizing 10- folds stratified cross validation. LMT-1 yields a tree of 48 leaves and 95 of size with 90.88% of accuracy, while both LMT-2 and LMT-3 provide two trees of 1 leaf and 1 of size with 99.28% and 99.37% of accuracy respectively. Experiments show that the proposed hierarchical classification methodology gives a better performance compared to other prevailing approaches.

Authors and Affiliations

Masun Nabhan Homsi

Keywords

Related Articles

Efecto de la ozonoterapia sobre el intervalo parto-celo y la fertilidad en vacas lecheras

En la vaca lechera la atención médica del puerperio es fundamental en los programas de manejo reproductivo. Durante este periodo se diagnostican y tratan patologías del útero con el propósito de acortar el periodo de e...

Los PLE’s en el desarrollo de competencias cognitivas desde la metodología sistémica en estudiantes universitarios

The research focused on the evaluation of the application of personal learning environments to first semester students of the Biology and Chemistry program at the Universidad Nacional de Chimborazo (UNACH), with respec...

Determinación de adulterantes en leche cruda de vaca en centros de acopio, medios de transporte y ganaderías de la provincia del Cañar, Ecuador

Para ser comercializada y procesada en la industria, la leche de vaca debe cumplir con una serie de requisitos en lo referente a su composición físico-química, sus características organolépticas, además de no contener...

La relación del logro de la lectura con la lateralidad, el movimiento ocular sacádico y el color en los niños

Several authors consider reading an important activity in school, professional and personal life. Perceptual processes, hemispheric lateralization, vision and phonological awareness are factors that intervene in readin...

Propuesta metodológica de evaluación de seguridad para aplicaciones de Mobile Cloud Computing

A raíz de los nuevos avances tecnológicos en los dispositivos móviles, éstos están siendo cada vez más utilizados para realizar tareas complejas, sin embargo existen temas que limitan su utilización en procesos que dem...

Download PDF file
  • EP ID EP41975
  • DOI -
  • Views 203
  • Downloads 0

How To Cite

Masun Nabhan Homsi (2014). Multi-class sentiment analysis using a hierarchical logistic model tree approach. MASKANA, 5(5), -. https://europub.co.uk/articles/-A-41975