Abstract：To improve the ability to predict the evolution trend of public opinion, a public opinion evolution trend prediction model based on an improved wolf pack algorithm and optimized long-short term memory neural network is proposed. Use Halton Sequence to initialization to improve population diversity. Design step factor to perform Gauss-Sine perturbation transformation to improve wolf group exploration and development capabilities. Combine with the spiral in the whale optimization algorithm to improve the siege mechanism to enhance the local search ability of wolves. The bidirectional memory population is used to increase the cooperative ability of the wolf pack. The improved wolf pack algorithm (IWPA) is applied to the hyperparameter prediction of the LSTM neural network. Using keywords such as “COVID-19” and “Food Safety”, the experiment proves that the IWPA-LSTM neural network public opinion evolution prediction model has good accuracy and generality. The model is suitable for the prediction of various public opinion evolution trends.
李若晨, 肖人彬. 基于改进狼群算法优化LSTM网络的舆情演化预测[J]. 复杂系统与复杂性科学, 2024, 21(1): 1-11.
LI Ruochen, XIAO Renbin. Public Opinion Evolution Prediction Based on LSTM Network Optimized by an Improved Wolf Pack Algorithm[J]. Complex Systems and Complexity Science, 2024, 21(1): 1-11.
[1] 于同洋, 肖人彬, 侯俊东. 网络舆情结构逆转建模与仿真:基于改进Deffuant模型[J]. 复杂系统与复杂性科学, 2019, 16(3): 30-39. YU T Y, XIAO R B, HOU J D. Modeling and simulation of network public opinion structure reversal: based on an improved Deffuant model[J]. Complex Systems and Complexity Science, 2019, 16 (3): 30-39. [2] 张轩宇, 陈曦, 肖人彬. 后真相时代基于敌意媒体效应的观点演化建模与仿真[J]. 复杂系统与复杂性科学, 2023, 20(3): 44-51,59. ZHANG X Y, CHEN X, XIAO R B. Modeling and simulation of viewpoint evolution based on hostile media effect in the post truth era [J]. Complex Systems and Complexity Science, 2023, 20(3): 44-51,59. [3] 刘举胜, 何建佳, 韩景倜, 等. 观点动力学研究现状及进展述评[J]. 复杂系统与复杂性科学, 2021, 18(2): 9-20. LIU J S, HE J J, HAM J T, et al. Review on the research status and progress of viewpoint dynamics[J]. Complex Systems and Complexity Science, 2021, 18 (2): 9-20 [4] 张和平, 陈齐海. 基于灰色马尔可夫模型的网络舆情预测研究[J]. 情报科学, 2018, 36(1): 75-79. ZHANG H P, CHEN Q H. Research on internet public opinion prediction based on grey Markov model [J]. Information Science, 2018, 36(1): 75-79. [5] Anjaria M, Guddeti R. Influence factor-based opinion mining of twitter data using supervised learning[C]//2014 Sixth International Conference on Communication Systems and Networks (COMSNETS). Bangalore, India: IEEE, 2014. [6] 林玲, 陈福集, 谢加良, 等. 基于改进灰狼优化支持向量回归的网络舆情预测[J]. 系统工程理论与实践, 2022,42(2): 487-498. LIN L, CHEN F J, XIE J L,et al. Network public opinion prediction based on improved grey wolf optimization support vector regression[J]. Systems Engineering Theory and Practice, 2022, 42(2): 487-498. [7] 野雪莲, 杨孔雨. 舆情趋势预测中神经网络的优化算法[J]. 网络新媒体技术, 2016, 5(1): 33-37,51. YE X L,YANG K Y. Neural network optimization algorithm in public opinion trends prediction[J]. Journal of Network New Media, 2016, 5(1): 33-37,51. [8] 孙靖超, 周睿, 李培岳, 等. 基于循环神经网络的网络舆情趋势预测研究[J]. 情报科学, 2018, 36(8):118-122,127. SUN J C, ZHOU R, LI P Y,et al. Research on network public opinion trend prediction based on recurrent neural network[J]. Information Science, 2018, 36(8): 118-122,127. [9] 傅丽芳, 赵菲菲. 基于注意力机制LSTM模型的农业舆情预测与分析[J]. 数学的实践与认识, 2021, 51(17): 64-76. FU L F, ZHAO F F. A forecasting method of agricultural public opinion based on Lda-Lstm-Attn model[J]. Journal of Mathematics in Practice and Theory, 2021, 51(17): 64-76. [10] 魏腾飞, 潘庭龙. 基于改进PSO优化LSTM网络的短期电力负荷预测[J]. 系统仿真学报, 2021, 33(8): 1866-1874. WEI T F, PAN T L.Short-term power load forecasting based on LSTM neural network optimized by improved PSO[J]. Journal of System Simulation, 2021, 33(8): 1866-1874. [11] 于永进, 姜雅男, 李长云. 基于WOA-LSTM模型的机-热老化绝缘纸剩余寿命预测方法[J]. 电工技术学报, 2022, 37(12): 3162-3171. YU Y J, JIANG Y N, LI C Y.Prediction method of insulation paper remaining life with mechanical-thermal synergy based on whale optimization algorithm-Long-Short Term Memory model[J]. Transactions of China Electrotechnical Society, 2022, 37(12):3162-3171. [12] 吴虎胜, 张凤鸣, 吴庐山. 一种新的群体智能算法——狼群算法[J]. 系统工程与电子技术, 2013, 35(11): 2430-2438. WU H S, ZHANG F M, WU L S. A new swarm intelligence algorithm—wolf packalgorithm[J]. Systems Engineering and Electronics, 2013, 35(11): 2430-2438. [13] 薛俊杰, 王瑛, 李浩, 等. 一种狼群智能算法及收敛性分析[J]. 控制与决策, 2016, 31(12):2131-2139. XUE JJ, WANG Y, LI H, et al. A smart wolf pack algorithm and its convergence analysis[J]. Control and Decision, 2016, 31 (12): 2131-2139. [14] 叶勇, 张惠珍. 多配送中心车辆路径问题的狼群算法[J]. 计算机应用研究, 2017,34(9):36-39. YE Y, ZHANG H Z.Wolf pack algorithm for multi-depot vehicle routing problem[J]. Application Research of Computers, 2017,34(9): 36-39. [15] 尹怀仙, 王凯, 张铁柱, 等. 基于PSO-BP神经网络的城轨列车转向架轮对轴箱故障预测[J]. 复杂系统与复杂性科学, 2015, 12(4): 97-103. YIN H X, WANG K, ZHANG T Z,et al. Fault prediction based on PSO-BP neural network about wheel and axle box of bogie in urban rail train[J]. Complex Systems and Complexity Science, 2015, 12(4): 97-103 [16] 胡亮, 肖人彬, 王英聪. 蜂群激发抑制算法及其在交通信号配时中的应用[J]. 复杂系统与复杂性科学, 2019, 16(2): 9-18,40. HU L, XIAO R B, WANG Y C.Bee colony activating-inhibition algorithm and its application in traffic signal timing[J]. Complex Systems and Complexity Science, 2019, 16(2): 9-18,40. [17] 韩忠华, 刘约翰, 李曼, 等. 改进狼群算法求解模具在模台上组合分配问题[J]. 系统仿真学报, 2021, 33(1): 127-140. HAN Z H, LIU Y H, LI M, SUN LL, et al. Improved wolf pack algorithm for distribution of molds on molds table[J]. Journal of System Simulation, 2021, 33(1): 127-140. [18] WU H S, ZHANG F M. A uncultivated wolf pack algorithm for high-dimensional functions and its application in parameters optimization of PID controller[C]//2014 IEEE Congress on Evolutionary Computation (CEC). Beijing, China: IEEE, 2014. [19] 刘东阳, 查文文, 陶亮, 等. 基于LSTM和SMC的农用履带机器人轨迹跟踪控制[J]. 系统仿真学报, 2023, 35(4): 747-759. LIU D Y, ZHA WW, TAO L, et al. Trajectory control of crawler robot based on LSTM and SMC [J]. Journal of System Simulation, 2023, 35(4): 747-759. [20] EOM G, BYEON H. Development of keyword trend prediction models for obesity before and after the Covid-19 pandemic using RNN and LSTM: analyzing the news big data of South Korea[J]. Frontiers in Public Health, 2022, 10: 894266. [21] DU B G, HUANG S, GUO J, et al. Interval forecasting for urban water demand usingPSO optimized KDE distribution and LSTM neural networks[J]. Applied Soft Computing, 2022, 122: 108875. [22] 陈暄, 孟凡光, 吴吉义. 求解大规模优化问题的改进狼群算法[J]. 系统工程理论与实践, 2021, 41(3): 790-808. CHEN X, MENG F G, WU J Y.Improved wolf pack algorithm for large-scale optimization problems[J]. Systems Engineering Theory and Practice, 2021, 41(3): 790-808. [23] GAO Y J, ZHANG F M, ZHAO Y, et al. Quantum-inspired wolf pack algorithm to solve the 0-1 knapsack problem[J]. Mathematical Problems in Engineering, 2018(4): 5327056. [24] 刘成汉, 何庆. 融合多策略的黄金正弦黑猩猩优化算法[J]. 自动化学报, 2023, 49(11): 2360-2373. LIU C H, HE Q.Golden sine chimp optimization algorithm integrating multiple strategies[J]. Acta Automatica Sinica, 2023, 49(11): 2360-2373. [25] MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67. [26] 罗辞勇, 陈民铀, 张聪誉. 采用循环拥挤排序策略的改进NSGA-Ⅱ算法[J]. 控制与决策, 2010, 25(2): 227-231. LUO C Y, CHEN M Y, ZHANG C Y.Improved NSGA-Ⅱ algorithm with circular crowded sorting[J]. Control and Decision, 2010, 25(2): 227-231. [27] 王艳娇, 马春蕾. 基于记忆策略的动态离子运动优化算法[J]. 吉林大学学报(工学版), 2020, 50(3): 1047-1060. WANG Y J, MA C L.Dynamic ion motion optimization algorithm based on memory strategy[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(3): 1047-1060. [28] 汪慎文, 丁立新, 谢承旺, 等. 应用精英反向学习策略的混合差分演化算法[J]. 武汉大学学报(理学版), 2013, 59(2): 111-116. WANG S W, DING L X, XIE C W, et al. A hybrid differential evolution with elite opposition-based learning[J]. Journal of Wuhan University (Natural Science Edition), 2013, 59(2): 111-116. [29] HUANG Z H, WEI X, KAI Y. Bidirectional LSTM-CRF models for sequencetagging[DB/OL]. [2022-01-30]. https://doi.org/10.48550/arXiv.1508.01991 [30] 王鑫, 吴际, 刘超, 等. 基于LSTM循环神经网络的故障时间序列预测[J]. 北京航空航天大学学报, 2018, 44(4): 772-784. WANG X, WU J, LIU C, et al.Exploring LSTM-based recurrent neural network for failure time series prediction[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(4): 772-784. [31] XIAO R B, YU T Y, HOU J D. Modeling and simulation of opinion natural reversal dynamics with opinion leader based on HK bounded confidence model[J]. Complexity, 2020(1): 7360302. [32] 刘琪, 肖人彬. 观点动力学视角下基于意见领袖的网络舆情反转研究[J]. 复杂系统与复杂性科学, 2019, 16(1): 1-13. LIU Q, XIAO R B. An opinion dynamics approach to public opinion reversion with the guidance of opinion leaders[J]. Complex Systems and Complexity Science, 2019, 16(1): 1-13. [33] 刘巧玲, 李劲, 肖人彬. 基于参数反演的网络舆情传播趋势预测——以新浪微博为例[J]. 计算机应用, 2017, 37(5): 1419-1423. Liu Q L, Li J, Xiao R B.Trend prediction of public opinion propagation based on parameter inversion—an empirical study on Sina micro-blog [J]. Journal of Computer Applications, 2017, 37(5): 1419-1423. [34] WU H S, XIAO R B.Flexible wolf pack algorithm for dynamic multidimensional knapsack problems[J]. Research, 2020(1): 174-186. [35] LI J H, ZHU D S, LI C X. Comparative analysis of BPNN, SVR, LSTM, Random Forest, and LSTM-SVR for conditional simulation of non-Gaussian measured fluctuating wind pressures[J]. Mechanical Systems & Signal Processing, 2022, 178: 109285.
