- Title
- Multi-PSO based classifier selection and parameter optimisation for sentiment polarity prediction
- Creator
- Budhi, Gregorius Satia; Chiong, Raymond; Hu, Zhongyi; Pranata, Ilung; Dhakal, Sandeep
- Relation
- 2018 IEEE Conference on Big Data and Analytics (ICBDA). 2018 IEEE Conference on Big Data and Analytics (ICBDA) (Langkawi, Malaysia 21-22 November, 2018) p. 68-73
- Publisher Link
- http://dx.doi.org/10.1109/ICBDAA.2018.8629593
- Publisher
- Institute of Electrical and Electronics Engineers (IEEE)
- Resource Type
- conference paper
- Date
- 2018
- Description
- In the big data era, machine learning algorithms are extensively used for sentiment polarity prediction. However, identifying the correct machine learning algorithm and its parameter settings for the problem at hand can be a difficult task. We propose a system based on Particle Swarm Optimisation (PSO) to find the best machine learning algorithm and optimise its parameters for sentiment polarity prediction. The system’s design consists of two layers, namely a multi-PSO layer and a knockout layer. From experimental results, we find that each PSO in the multi-PSO layer could optimise the parameters of the classifiers processed. Overall, the system is able to determine the best classifier from the collection of processed classifiers and also provide quasi-optimal parameters for the classifier to predict the sentiment polarity of customer reviews.
- Subject
- machine learning; particle swarm optimisation; sentiment polarity prediction
- Identifier
- http://hdl.handle.net/1959.13/1404323
- Identifier
- uon:35315
- Identifier
- ISBN:9781538671283
- Language
- eng
- Reviewed
- Hits: 1425
- Visitors: 1395
- Downloads: 0
| Thumbnail | File | Description | Size | Format |
|---|