In supervised learning, new data is labelled based on experience gained from existing sentiment analysis models. However, the existing system will never update its knowledge with new data. The proposed model uses a multi-agent Aspect-based Deep Reinforcement Learning Sentiment Analysis to learn from the first information without any guidance gain knowledge and make decisions. By learning from the data it receives, it updates its knowledge and improves its intelligence. Consequently, the decision changes over time. This scenario can be used by online shopping sites to analyze sentiments in the reviews of their products. As a result, other customers on that site can effectively analyze the sentiments of premium customers.
AydinC. R.GüngörT. (2020). Combination of recursive and recurrent neural networks for aspect based sentiment analysis using inter-aspect relations. IEEE Access, 8, 77820–77832. https://doi.org/10.1109/ACCESS.2020.2990306
2.
ChuT.WangJ.CodecàL.LiZ. (2020). Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Transactions on Intelligent Transportation Systems, 21(3), 1086–1095. https://doi.org/10.1109/TITS.2019.2901791
3.
Crop Yield Prediction Using Deep Reinforcement Learning Model for Sustainable Agrarian Applications (2020).
4.
IqbalA.AminR.IqbalJ.AlroobaeaR.BinmahfoudhA.HussainM. (2022). Sentiment analysis of consumer reviews using deep learning. Sustainability, 14(17), 10844. https://doi.org/10.3390/su141710844
5.
KeneshlooY.ShiT.RamakrishnanN.ReddyC. K. (2020). Deep reinforcement learning for sequence-to-sequence models. IEEE Transactions on Neural Networks and Learning Systems, 31(7).
6.
KhardeV.SonawaneP. (2016). Sentiment analysis of twitter data: survey of techniques. arXiv 8 2016, arXiv:1601.06971.
7.
KreningS.HarrisonB.FeighK. M.IsbellC. L.RiedlM.ThomazA. (2017). Learning from explanations using sentiment and advice in RL. IEEE Transactions on Cognitive and Developmental Systems, 9(1), 44–55. https://doi.org/10.1109/TCDS.2016.2628365
8.
KuangM.SafaR.EdalatpanahS. A.KeyserR. S. (2023). A hybrid deep learning approach for sentiment analysis in product reviews. Facta Universitatis, Series: Mechanical Engineering, 21(3), 479–500. https://doi.org/10.22190/FUME230901038K
9.
LakomkinE.ZamaniM. A.WeberC.MaggS.WermterS. (2018). EmoRL continuous acoustic emotion classification using deep reinforcement learning. IEEE International Conference on Robotics and Automation (ICRA). 978-1-5386-3081 5/18.
MahmudM.KaiserM. S.HussainA. (2018). Applications of deep learning and reinforcement. IEEE Transactions on Neural Networks and Learning Systems, 29(6), 2063–2079. https://doi.org/10.1109/TNNLS.2018.2790388
12.
MaoY.LiuQ.ZhangY. (2024). Sentiment analysis methods, applications, and challenges: A systematic literature review. Journal of King Saud University - Computer and Information Sciences, 36(4), 102048. https://doi.org/10.1016/j.jksuci.2024.102048
13.
MarksC.AllenL.GigliottiF.BusanaF.GonzalezT.LindemanM.FisherP. (2004). Evaluation of the tranquilliser trap device (TTD) for improving the humaneness of dingo trapping. Animal Welfare, 13, 393–399. 34. https://doi.org/10.1017/S0962728600028645
14.
NguyenT. T.NguyenN. D.NahavandiS. (2020). Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications. IEEE Transactions on Cybernetics, 50(9), 3826–3839. https://doi.org/10.1109/TCYB.2020.2977374
15.
NguyenH.VeluchamyA.DiopM.IqbalR. (2018). Comparative study of sentiment analysis with product reviews using machine learning and lexicon-based approaches. SMU Data Science Review, 1, 7.
16.
PengY.ZhangJ.YeZ. (2020). Deep reinforcement learning for image hashing. IEEE Transactions on Multimedia, 22(8), 2061–2073. https://doi.org/10.1109/TMM.2019.2951462
17.
PröllochsN.FeuerriegelS.LutzB.NeumannD. (2020). Negation scope detection for sentiment analysis A reinforcement learning framework for replicating human interpretations. Information Sciences, 536(2020), 205–221. https://doi.org/10.1016/j.ins.2020.05.022
18.
QiuX.LiuL.ChenW.HongZ.ZhengZ. (2019). Online deep reinforcement learning for computation offloading in blockchain empowered mobile edge computing. IEEE Transactions on Vehicular Technology, 68(8), 8050–8062. https://doi.org/10.1109/TVT.2019.2924015
19.
RenZ.DongD.LiH.ChenC. (2018). Self-paced prioritized curriculum learning with coverage penalty in deep reinforcement learning. IEEE Transactions on Neural Networks and Learning Systems, 29(6), 2216–2226. https://doi.org/10.1109/TNNLS.2018.2790981
20.
TanK. L.LeeC. P.LimK. M. (2023). A survey of sentiment analysis: Approaches, datasets, and future research. Applied Sciences, 13(7), 4550. https://doi.org/10.3390/app13074550
21.
WuJ.JiT. (2016). Deep Learning for Amazon Food Review Sentiment Analysis. Stanford University.
22.
YangZ.MerrickK.JinL.AbbassH. A. (2018). Hierarchical deep reinforcement learning for continuous action control. IEEE Transactions on Neural Networks and Learning Systems, 29(11), 5174–5184. https://doi.org/10.1109/TNNLS.2018.2805379
23.
YangM.QuQ.ShenY.LeiK.ZhuJ. (2020). Cross-domain aspect/sentiment-aware abstractive review summarization by combining topic modeling and deep reinforcement learning. Neural Computing and Applications, 32, 6421–6421.
24.
YunS.ChoiJ.YooY. (2018). Action-driven visual object tracking with deep reinforcement learning. IEEE Transactions on Neural Networks and Learning Systems, 29(6), 2239–2252. https://doi.org/10.1109/TNNLS.2018.2801826
25.
ZhangC. (2019). Sentiment analysis and deep reinforcement learning for algorithmic trading. Semantic Scholar.
26.
ZhouY.ZhangL.DuanX. (2019). Word level sentiment analysis with reinforcement learning. IOP Conference Series: Materials Science and Engineering, 490: 062063. https://doi.org/10.1088/1757-899X/490/6/062063
