Please wait a minute...
Data Analysis and Knowledge Discovery  2020, Vol. 4 Issue (4): 15-26    DOI: 10.11925/infotech.2096-3467.2019.0500
Current Issue | Archive | Adv Search |
Analyzing Public Sentiments from the Perspective of City Profiles
Ye Guanghui(),Zeng Jieyan,Hu Jinglan,Bi Chongwu
School of Information Management, Central China Normal University, Wuhan 430079, China
Download: PDF (1054 KB)   HTML ( 15
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This study constructs an evolution model for social sentiment analysis from the perspective of city profiles, aiming to grasp city dynamics, guide public opinions, as well as identify and predict potential issues. [Methods] We firstly used the LDA2Vec algorithm to extract city themes from each time window. Then, we applied a dictionary-based sentiment analysis method to fine-grain the emotion categories of city themes, and calculated their emotional intensities. Finally, we tracked city events arising changes of public sentiments with the TF-IDF algorithm, and built the ARMA model to predict social sentiment trends. [Results] Our model’s accuracy rate for predicting emotional intensity of “like” reached 97%, while those of the “dislike” scores were up to 90%. [Limitations] We did not include unexpected events as an influencing factor to the proposed model. [Conclusions] Our method could effectively identify city events and predict emotional changes of public opinions.

Key wordsCity      Profile      Emotional      Evolution      LDA2Vec      Public      Opinion      Monitoring     
Received: 12 May 2019      Published: 01 June 2020
ZTFLH:  TP393  
Corresponding Authors: Ye Guanghui     E-mail: 3879-4081@163.com

Cite this article:

Ye Guanghui,Zeng Jieyan,Hu Jinglan,Bi Chongwu. Analyzing Public Sentiments from the Perspective of City Profiles. Data Analysis and Knowledge Discovery, 2020, 4(4): 15-26.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2019.0500     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2020/V4/I4/15

Analysis Process of Public Emotion Evolution
初始情感类别 否定词修饰后的情感类别
a×乐
b×好
Emotion Conversion Modified by Negative Word
强度 程度副词 个数
2.0 百分之百、倍加、备至、非常、极度、极端…… 38
1.8 越、越发、愈发、愈加、过度、过分、过火…… 29
1.5 不过、不少、不胜、多加、多么、分外、格外…… 13
1.2 大不了、多、更、更加、更进一步、更为、还要…… 12
0.8 略、略加、略略、略微、略为、蛮、稍、稍稍…… 15
0.5 半点、不大、不丁点儿、不甚、不怎么、丝毫…… 12
Degree Adverb List
时间 主题编号 主题 主题特征词(部分)
2014.01-2014.06 Topic1-1 城市文化 热干面 黄鹤楼 大学生 热情 耿直
Topic1-2 城市交通 司机 公交车 急 拥堵 混乱
Topic1-3 城市发展 科教 满城挖 城乡结合部 经济 物价
Topic1-4 城市环境 气候 冬冷夏热 天气 热 火炉
2014.07-2014.12 Topic2-1 城市文化 热干面 武汉大学 樱花 美食 VOX
Topic2-2 城市交通 司机 剽悍 暴躁 公交车 堵
Topic2-3 城市发展 满城挖 人多 学校 生活 服务
Topic2-4 城市环境 热 火炉 环境 烟尘 脏乱差
2015.01-2015.06 Topic3-1 城市文化 热干面 小龙虾 武汉大学 东湖 朋克
Topic3-2 城市交通 司机 出租车 拒载 交通 堵
Topic3-3 城市发展 人才 留不住 工资水平 生活气息 汉口
Topic3-4 城市环境 天气 夏天 冬天 脏乱 拥挤
2015.07-2015.12 Topic4-1 城市文化 黄鹤楼 小龙虾 湖北省博物馆 武汉大学
Topic4-2 城市交通 公交车 地铁 光谷 拥堵 堵
Topic4-3 城市发展 满城挖 修路 人文 发展 很大
Topic4-4 城市环境 天气 热 看海 环境 不好
2016.01-2016.06 Topic5-1 城市文化 樱花 昙华林 东湖 周黑鸭 鸭脖
Topic5-2 城市交通 公交车 出租车 堵 交通 拥挤
Topic5-3 城市发展 房价 工资 年轻人 大学生 满城挖
Topic5-4 城市环境 夏天 热 空气 雾霾 看海
2016.07-2016.12 Topic6-1 城市文化 东湖 长江大桥 风景 轮渡 莲藕
Topic6-2 城市交通 司机 暴躁 九省通衢 堵车 严重
Topic6-3 城市发展 建设 变化 道路 经济 改善
Topic6-4 城市环境 冬冷夏热 霾 灰尘 空气 糟糕
2017.01-2017.06 Topic7-1 城市文化 鸭脖 热干面 东湖 武汉大学 码头文化
Topic7-2 城市交通 交通 拥堵 便利 公交车 开车
Topic7-3 城市发展 市井气息 人多 外地人 就业 商业
Topic7-4 城市环境 夏天 热 冬天 暴雨 潮湿
2017.07-2017.12 Topic8-1 城市文化 长江大桥 夜景 建筑 黄鹤楼 热干面
Topic8-2 城市交通 司机 脾气 光谷 拥堵 混乱
Topic8-3 城市发展 满城挖 每天 不一样 房价 工资
Topic8-4 城市环境 夏天 雨季 热 天气 灰蒙蒙
2018.01-2018.06 Topic9-1 城市文化 过早 热干面 豆皮 人情味 生活气息
Topic9-2 城市交通 公交车 超速 凶猛 过山车 晕车
Topic9-3 城市发展 道路 施工 建设 发展 迅速
Topic9-4 城市环境 冬天 夏天 气候 恶劣 变化
2018.07-2018.12 Topic10-1 城市文化 过早 热干面 豆皮 市井 历史
Topic10-2 城市交通 出租车 过山车 超速 晕车 拥堵
Topic10-3 城市发展 修路 便利 教育 军运会 宜居
Topic10-4 城市环境 气候 冬冷夏热 空气 差 湿气
Themes Distribution of City Profiles
Emotion Type and Intensity Corresponding to Different Topics in Each Time Window
Theme Emotional Evolution Curve
主题编号 情感极性
临界点类型
关键词
Topic5-2 好→恶 司机 绕路 堵车 严重 光谷 不礼让
Topic6-2 恶→好 公交 地铁 便宜 交通 枢纽 便利
Topic3-4 好→恶 冬冷 夏热 雾霾 四季 随机 播放
Topic4-4 恶→好 天气 阴晴 不定 脏乱 街道 改善
Topic5-4 好→恶 气候 多变 很热 火炉 雾霾 脏话
Topic6-4 恶→好 风景 落雁岛 环境 美 大江 大湖
Topic8-4 好→恶 雨 多 灰尘 湿热 看海 石楠花
Text Keywords at Turning Point
序列名称 估计方程 预测值 实际值
“好”情感值时间序列 Like(t)=α+εt 1 841 1 897
“恶”情感值时间序列 Unlike(t)=α+εt 872 972
Modeling and Prediction of Sentiment Time Series
[1] Gabrilovich E, Markovitch S. Computing Semantic Relatedness Using Wikipedia-Based Explicit Semantic Analysis[C]// Proceedings of the 20th International Joint Conference on Artificial Intelligence. 2007: 1606-1611.
[2] 马雯雯, 魏文晗, 邓一贵 . 基于隐含语义分析的微博话题发现方法[J]. 计算机工程与应用, 2014,50(1):96-100.
[2] ( Ma Wenwen, Wei Wenhan, Deng Yigui . Micro-blog Topic Detection Method Based on Latent Semantic Analysis[J]. Computer Engineering and Applications, 2014,50(1):96-100.)
[3] 吴妮, 赵捧未, 秦春秀 . 基于语义分析和相似强度的微博热点发现方法[J]. 现代图书情报技术, 2015(5):57-64.
[3] ( Wu Ni, Zhao Pengwei, Qin Chunxiu . Microblog Hotspot Detection Based on Semantic Analysis and Similarity Strength[J]. New Technology of Library and Information Service, 2015(5):57-64.)
[4] Chen M, Jin X, Shen D. Short Text Classification Improved by Learning Multi-Granularity Topics[C]// Proceedings of the 22nd International Joint Conference on Artificial Intelligence, Barcelona, Spain. 2011: 1776-1781.
[5] Wang Z, Ma L, Zhang Y. A Hybrid Document Feature Extraction Method Using Latent Dirichlet Allocation and Word2Vec[C]// Proceedings of the IEEE 1st International Conference on Data Science in Cyberspace. 2016: 98-103.
[6] Li C, Lu Y, Wu J, et al. LDA Meets Word2Vec: A Novel Model for Academic Abstract Clustering[C]// Proceedings of the 2018 International World Wide Web Conference. 2018: 1699-1706.
[7] Ekman P, Freisen W V, Ancoli S . Facial Signs of Emotional Experience[J]. Journal of Personality and Social Psychology, 1980,39(6):1125-1134.
doi: 10.1037/h0077722
[8] Plutchik R, Kellerman H. Emotion , Theory, Research, and Experience[M]. Academic Press, 1980.
[9] 梁承谋 . 七情说与现代情绪心理学[J]. 南京师大学报:社会科学版, 1996(4):64-67.
[9] ( Liang Chengmou . Seven Feelings and Modern Emotional Psychology[J]. Journal of Nanjing Normal University: Social Science Edition, 1996(4):64-67.)
[10] 徐琳宏, 林鸿飞, 潘宇 , 等. 情感词汇本体的构造[J]. 情报学报, 2008,27(2):180-185.
[10] ( Xu Linhong, Lin Hongfei, Pan Yu , et al. Constructing the Affective Lexicon Ontology[J]. Journal of the China Society for Scientific and Technical Information, 2008,27(2):180-185.)
[11] 王洪伟, 刘勰, 尹裴 , 等. Web文本情感分类研究综述[J]. 情报学报, 2010,29(5):931-938.
[11] ( Wang Hongwei, Liu Xie, Yin Pei , et al. Literature Review of Sentiment Classification on Web Text[J]. Journal of the China Society for Scientific and Technical Information, 2010,29(5):931-938.)
[12] AlSumait L, Barbará D, Domeniconi C. On-line LDA: Adaptive Topic Models for Mining Text Streams with Applications to Topic Detection and Tracking[C]// Proceedings of the 8th IEEE International Conference on Data Mining. IEEE, 2008: 3-12.
[13] 敦欣卉, 张云秋, 杨铠西 . 基于微博的细粒度情感分析[J]. 数据分析与知识发现, 2017,1(7):61-72.
[13] ( Dun Xinhui, Zhang Yunqiu, Yang Kaixi . Fine-grained Sentiment Analysis Based on Weibo[J]. Data Analysis and Knowledge Discovery, 2017,1(7):61-72.)
[14] Fu X, Liu G, Guo Y , et al. Multi-aspect Sentiment Analysis for Chinese Online Social Reviews Based on Topic Modeling and HowNet Lexicon[J]. Knowledge-Based Systems, 2013,37:186-195.
doi: 10.1016/j.knosys.2012.08.003
[15] 杨超, 冯时, 王大玲 , 等. 基于情感词典扩展技术的网络舆情倾向性分析[J]. 小型微型计算机系统, 2010,31(4):691-695.
[15] ( Yang Chao, Feng Shi, Wang Daling , et al. Analysis on Web Public Opinion Orientation Based on Extending Sentiment Lexicon[J]. Journal of Chinese Computer Systems, 2010,31(4):691-695.)
[16] 朱晓霞, 宋嘉欣, 孟建芳 . 基于主题-情感挖掘模型的微博评论情感分类研究[J]. 情报理论与实践, 2019,42(5):159-164.
[16] ( Zhu Xiaoxia, Song Jiaxin, Meng Jianfang . Research on the Classification of Emotion in Microblog Comments Based on the Theme-Emotion Mining Model[J]. Information Studies: Theory & Application, 2019,42(5):159-164.)
[17] Lin Y R, Margolin Ds. The Ripple of Fear, Sympathy and Solidarity During the Boston Bombings[J]. EPJ Data Science, 2014, 3(1): Article No. 31.
doi: 10.1140/epjds/s13688-014-0031-z
[18] Van Goethe A, Staals F, Löffler M , et al. Multi-Granular Trend Detection for Time-Series Analysis[J]. IEEE Transactions on Visualization and Computer Graphics, 2016,23(1):661-670.
doi: 10.1109/TVCG.2016.2598619
[19] Iwata T, Yamada T, Sakurai Y, et al. Online Multiscale Dynamic Topic Models[C]// Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2010: 663-672.
[20] 王秀芳, 盛姝, 路燕 . 一种基于话题聚类及情感强度的微博舆情分析模型[J]. 数据分析与知识发现, 2018,2(6):37-47.
[20] ( Wang Xiufang, Sheng Shu, Lu Yan . Analyzing Public Opinion from Microblog with Topic Clustering and Sentiment Intensity[J]. Data Analysis and Knowledge Discovery, 2018,2(6):37-47.)
[21] 唐晓波, 童海燕, 严承希 . 基于话题情感强度的微博舆情分析[J]. 图书馆学研究, 2014(17):85-93.
[21] ( Tang Xiaobo, Tong Haiyan, Yan Chengxi . Microblog Public Opinion Analysis Based on Emotional Intensity of the Topic[J]. Research on Library Science, 2014(17):85-93.)
[22] Blei D M, Lafferty J D. Dynamic Topic Models[C]// Proceedings of the 23rd International Conference on Machine Learning. ACM, 2006: 113-120.
[23] 李慧, 胡云凤 . 基于动态情感主题模型的在线评论分析[J]. 数据分析与知识发现, 2017,1(9):79-87.
[23] ( Li Hui, Hu Yunfeng . Analyzing Online Reviews with Dynamic Sentiment Topic Model[J]. Data Analysis and Knowledge Discovery, 2017,1(9):79-87.)
[24] 李超雄, 黄发良, 温肖谦 , 等. 基于动态主题情感混合模型的微博主题情感演化分析方法[J]. 计算机应用, 2015,35(10):2905-2910.
doi: 10.11772/j.issn.1001-9081.2015.10.2905
[24] ( Li Chaoxiong, Huang Faliang, Wen Xiaoqian , et al. Evolution Analysis Method of Microblog Topic-Sentiment Based on Dynamic Topic Sentiment Combining Model[J]. Journal of Computer Applications, 2015,35(10):2905-2910.)
doi: 10.11772/j.issn.1001-9081.2015.10.2905
[25] Strapparava C, Mihalcea R. Learning to Identify Emotions in Text[C]// Proceedings of the 2008 ACM Symposium on Applied Computing. ACM, 2008: 1556-1560.
[26] 韩忠明, 张玉沙, 张慧 , 等. 有效的中文微博短文本倾向性分类算法[J]. 计算机应用与软件, 2012,29(10):89-93.
[26] ( Han Zhongming, Zhang Yusha, Zhang Hui , et al. On Effective Short Text Tendency Classification Algorithm for Chinese Microblogging[J]. Computer Applications and Software, 2012,29(10):89-93.)
[27] 王铁套, 王国营, 陈越 , 等. 基于语义模式与词汇情感倾向的舆情态势研究[J]. 计算机工程与设计, 2012,33(1):74-77.
[27] ( Wang Tietao, Wang Guoying, Chen Yue , et al. Study of Network Public Opinion Situation Based on Semantic Pattern and Word Sentiment Orientation[J]. Computer Engineering and Design, 2012,33(1):74-77.)
[28] 杜振雷 . 面向微博短文本的情感分析研究[D]. 北京: 北京信息科技大学, 2013.
[28] ( Du Zhenlei . A Sentiment Analysis Research on Microblog Short Text[D]. Beijing: Beijing Information Science and Technology University, 2013.)
[29] 郑丽娟, 王洪伟, 郭恺强 . 基于情感词模糊统计的网络评论情感强度的研究[J]. 系统管理学报, 2014,23(3):324-330.
[29] ( Zheng Lijuan, Wang Hongwei, Guo Kaiqiang . Sentiment Intensity of Online Reviews Based on Fuzzy-Statistics of Sentiment Words[J]. Journal of Systems & Management, 2014,23(3):324-330.)
[30] 安璐, 吴林 . 融合主题与情感特征的突发事件微博舆情演化分析[J]. 图书情报工作, 2017,61(15):120-129.
[30] ( An Lu, Wu Lin . An Integrated Analysis of Topical and Emotional Evolution of Microblog Public Opinions on Public Emergencies[J]. Library and Information Service, 2017,61(15):120-129.)
[31] 路永和, 李焰锋 . 改进TF-IDF算法的文本特征项权值计算方法[J]. 图书情报工作, 2013,57(3):90-95.
doi: 10.7536/j.jssn.0252-3116.2013.03.017
[31] ( Lu Yonghe, Li Yanfeng . Improvement of Text Feature Weighting Method Based on TF-IDF Algorithm[J]. Library and Information Service, 2013,57(3):90-95.)
doi: 10.7536/j.jssn.0252-3116.2013.03.017
[32] Box G E P, Pierce D A, Newbold P . Estimating Trend and Growth Rates in Seasonal Time Series[J]. Journal of the American Statistical Association, 1981,82(397):276-282.
doi: 10.1080/01621459.1987.10478430
[33] Giffinger R, Gudrun H . Smart Cities Ranking: An Effective Instrument for the Positioning of the Cities?[J]. Architecture City & Environment, 2010,6(12):7-26.
[34] Lombardi P, Giordano S, Farouh H , et al. Modelling the Smart City Performance[J]. Innovation the European Journal of Social Science Research, 2012,25(2):137-149.
doi: 10.1080/13511610.2012.660325
[1] Fan Tao,Wang Hao,Wu Peng. Sentiment Analysis of Online Users' Negative Emotions Based on Graph Convolutional Network and Dependency Parsing[J]. 数据分析与知识发现, 2021, 5(9): 97-106.
[2] Wang Xiwei,Jia Ruonan,Wei Yanan,Zhang Liu. Clustering User Groups of Public Opinion Events from Multi-dimensional Social Network[J]. 数据分析与知识发现, 2021, 5(6): 25-35.
[3] Ma Yingxue,Zhao Jichang. Patterns and Evolution of Public Opinion on Weibo During Natural Disasters: Case Study of Typhoons and Rainstorms[J]. 数据分析与知识发现, 2021, 5(6): 66-79.
[4] Li Yueyan,Wang Hao,Deng Sanhong,Wang Wei. Research Trends of Information Retrieval——Case Study of SIGIR Conference Papers[J]. 数据分析与知识发现, 2021, 5(4): 13-24.
[5] Chen Jun,Liang Hao,Qian Chen. Studying Investment Decisions of Rewarded Crowdfunding Users with Emotional Distance and Text Analysis[J]. 数据分析与知识发现, 2021, 5(4): 60-71.
[6] Wang Nan,Li Hairong,Tan Shuru. Predicting of Public Opinion Reversal with Improved SMOTE Algorithm and Ensemble Learning[J]. 数据分析与知识发现, 2021, 5(4): 37-48.
[7] Shen Si,Li Qinyu,Ye Yuan,Sun Hao,Ye Wenhao. Topic Mining and Evolution Analysis of Medical Sci-Tech Reports with TWE Model[J]. 数据分析与知识发现, 2021, 5(3): 35-44.
[8] Xu Yabin, Sun Qiutian. Identifying Leaders and Dissemination Paths of Public Opinion[J]. 数据分析与知识发现, 2021, 5(2): 32-42.
[9] Cheng Tiejun, Wang Man, Huang Baofeng, Feng Lanping. Predicting Online Public Opinion in Emergencies Based on CEEMDAN-BP[J]. 数据分析与知识发现, 2021, 5(11): 59-67.
[10] Han Pu, Zhang Wei, Zhang Zhanpeng, Wang Yuxin, Fang Haoyu. Sentiment Analysis of Weibo Posts on Public Health Emergency with Feature Fusion and Multi-Channel[J]. 数据分析与知识发现, 2021, 5(11): 68-79.
[11] Wang Wei, Gao Ning, Xu Yuting, Wang Hongwei. Topic Evolution of Online Reviews for Crowdfunding Campaigns[J]. 数据分析与知识发现, 2021, 5(10): 103-123.
[12] Hua Bin, Wu Nuo, He Xin. Integrating Expert Reviews for Government Information Projects with Knowledge Fusion[J]. 数据分析与知识发现, 2021, 5(10): 124-136.
[13] Zheng Xinman, Dong Yu. Constructing Degree Lexicon for STI Policy Texts[J]. 数据分析与知识发现, 2021, 5(10): 81-93.
[14] Guan Peng,Wang Yuefen,Jin Jialin,Fu Zhu. Developments of Tech-Innovation Network for Patent Cooperation: Case Study of Speech Recognition in China[J]. 数据分析与知识发现, 2021, 5(1): 112-127.
[15] Chai Guorong,Wang Bin,Sha Yongzhong. Public Health Risk Forecasting with Multiple Machine Learning Methods Combined:Case Study of Influenza Forecasting in Lanzhou, China[J]. 数据分析与知识发现, 2021, 5(1): 90-98.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn