Sentiment analysis via multi-layer perceptron trained by meta-heuristic optimisation

Dabiah Ahmed Alboaneen, Huaglory Tianfield, Yan Zhang

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    178 Downloads (Pure)

    Abstract

    In this paper, a new tweet analysing approach is proposed, which is composed of two main phases; feature selection and tweets classification. In the first phase, mutual information (MI) is used to select the best set of features to reduce the feature dimensions. In the second phase, a metaheuristic algorithm is used to optimise weights and biases of multi-layer perceptrons (MLPs) network and then implemented to classify twitter sentiments. Experimental results on existing twitter dataset show better performance of the glowworm swarm optimisation (GSO) based MLP over genetic algorithm (GA )and biogeography-based optimisation (BBO) algorithms.
    Original languageEnglish
    Title of host publicationProceedings of 2017 IEEE International Conference on Big Data
    Subtitle of host publication2017 International Workshop on Big Data Analytics for Cyber Intelligence and Defense
    Number of pages6
    DOIs
    Publication statusPublished - 15 Jan 2018

    Keywords

    • sentiment analysis
    • twitter
    • multi-layer perceptrons
    • glowworm swarm optimisation
    • genetic algorithm
    • biogeography-based optimisation

    Fingerprint Dive into the research topics of 'Sentiment analysis via multi-layer perceptron trained by meta-heuristic optimisation'. Together they form a unique fingerprint.

  • Cite this

    Alboaneen, D. A., Tianfield, H., & Zhang, Y. (2018). Sentiment analysis via multi-layer perceptron trained by meta-heuristic optimisation. In Proceedings of 2017 IEEE International Conference on Big Data: 2017 International Workshop on Big Data Analytics for Cyber Intelligence and Defense https://doi.org/10.1109/BigData.2017.8258507