Combining Overall and Target Oriented Sentiment Analysis over Portuguese Text from Social Media
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2015, Vol 3, Issue 3
Abstract
This document describes an approach to perform sentiment analysis on social media Portuguese content. In a single system, we perform polarity classification for both the overall sentiment, and target oriented sentiment. In both modes we train a Maximum Entropy classifier. The overall model is based on BoW type features, and also features derived from POS tagging and from sentiment lexicons. Target oriented analysis begins with named entity recognition, followed by the classification of sentiment polarity on these entities. This classifier model uses features dedicated to the entity mention textual zone, including negation detection, and the syntactic function of the target occurrence segment. Our experiments have achieved an accuracy of 75% for target oriented polarity classification, and 97% in overall polarity.
Authors and Affiliations
José Saias, Ruben Silva, Eduardo Oliveira
Keywords
Related Articles
- EP ID EP278880
- DOI 10.14738/tmlai.33.1297
- Views 63
- Downloads 0
Integration of the ASR Toolkit Kaldi into a Domoticz Home Automation System
This paper presents the design and the implementation of an interface between Kaldi, automatic speech recognition toolkit, and a home automation system. This interface is based on Open Platform communication (OPC) protoc...
Performance Evaluation of Some Selected Sorting Algorithms by the Use of Halstead Complexity Metrics
Complexity is developed to demonstrate feasible metrics for process obtaining objectives and quantifiable measurement, which may have numerous valuable applications in schedule and budget planning, cost estimation and op...
Support Vector Machine Regression and Artificial Neural Network for Channel Estimation of LTE Downlink in High-Mobility Environments
In this paper we apply and assess the performance of support vector machine regression (SVR) and artificial neural network (ANN) channel estimation algorithms to the reference signal structure standardized for LTE Downli...
Novel Compact CPW LowPass Filter Integrating Periodic Triangle DGS Cells
In this paper, we introduce a new periodic structure for CPW of a low pass filter based on the DGS technique with triangle slot cell forme. The proposed structure is a minuature low pass filter that exhibits low insertio...
Pattern Based Melody Matching Approach to Music Information Retrieval
Digitization of music and advancements in information technology for sharing information on World Wide Web paved way for its availability in enormous quantities anywhere any time. Rather than retrieving annotated music i...