Emotion Mining and Analysis of Comments Based on Emotional Model——A Case Study on Book Reviews of Douban
Received date: 2018-09-07
Online published: 2025-04-28
[Purpose/significance] This study aims to explore the methods on extracting and visualizing users’ emotions from unstructured user-generated content, analyze user-generated content from a perceptual level, and discuss the related application prospects. [Method/process] The research took book reviews of Douban as analysis object. Emotional dictionary in Chinese domain and LDA latent topic model were used to refine the fine-grained emotional elements. And further, visualization techniques helped to analyze the emotional elements reflected in the review content. [Result/conclusion] The study found that both latent topic model and emotion dictionary can effectively extract the user emotion elements in the content of the review, even though some difference still exists, such as the emotional topic model can provide more exquisite results. By fine-tuning the application scenario, the methods used in this study can be applied to various forms of perceived utility mining tasks about reviews, like experience-based products recommendation.
Nie Hui , Liu Mengyuan . Emotion Mining and Analysis of Comments Based on Emotional Model——A Case Study on Book Reviews of Douban[J]. Knowledge Management Forum, 2018 , 3(6) : 313 -324 . DOI: 10.13266/j.issn.2095-5472.2018.030

表1 《小王子》情感主题与例句 |
| 主题 | 主要关键词 | 前20项占比 | 例句 |
| 1 | 喜欢、理解、纯真、享受、珍惜 | 32.4% | “……或许不同的人会有不同的理解……长大后才读完这本书,所以不可避免地喜欢那只狐狸……爱童话的人是拿一颗赤诚的心去读童话的……” |
| 2 | 重要、朋友、心灵、仰望、美好 | 32% | “……人们不再有时间去了解事情了,他们总是到商店里买现成的东西,却没有一家店贩卖友谊……真正重要的东西是肉眼看不到的……” |
| 3 | 孤独、奇怪、痛苦、寂寞、亲爱 | 13.1% | “……小王子与玫瑰花就此道别,他们彼此回到他们所习惯的,孤独的常态中……” |
| 4 | 幸福、爱情、美丽、愿意、耐心 | 11.5% | “……狐狸被这样的幸福淹没了。这就象花一样。如果你爱上了一朵生长在一颗星星上的花,那么夜间你看着天空就感到甜蜜愉快……” |
| 5 | 希望、喜欢、快乐、微笑、骄傲 | 11% | “……回忆的味道,就像柠檬草的香味。但是,是放下了的,还是会有余香的……” |
表2 《白夜行》情感主题与例句 |
| 主题 | 主要关键词 | 前20项占比 | 例句 |
| 1 | 爱情、绝望、希望、失去、伤害 | 35.1% | “……爱情是自私的,而感情,却真的真的,可以是无限大的。大于原罪和赎回,也大于希望与生命……” |
| 2 | 重要、理解、肯定、相信、获得 | 19.4% | “正好看到城下的分析,和我的理解基本相似……”“中文版白夜行的成功,50%的归功于原作,50%归功于翻译……” |
| 3 | 幸福、失去、伤害、不幸、伪装 | 19% | “……毫无疑问,她是一个受害者。但是在被禽兽折磨的过程中,她也异变成了一个禽兽,一个遗传了她母亲卑贱品格的女人……” |
| 4 | 怀疑、离婚、强暴、杀害、窃取 | 14.6% | “……怀疑雪穂把事件伪装成事故死,并且故意推迟了死亡的发现时间……高宮雪穂找到女性律师商量离婚的事……” |
| 5 | 人物、犯罪、献身、凶手、诡计 | 12% | “……唐泽和桐原都是彼此在黑暗中宝贵的第二道阳光,纵然桐原舍身,唐泽也只能毅然转身离去…… |
聂卉: 论文整体设计构思指导,数据收集整理,论文修改;
刘梦圆: 实验分析,论文初步撰写。
| [1] |
RAVI K. A survey on opinion mining and sentiment analysis: tasks, approaches and applications[J]. Knowledge-based systems, 2015, 89(C):14-46.
|
| [2] |
兰月新, 夏一雪, 刘冰月,等. 面向舆情大数据的网民情绪演化机理及趋势预测研究[J]. 情报杂志, 2017, 36(11):134-140.
|
| [3] |
张信东, 原东良. 基于微博的投资者情绪对股票市场影响研究[J]. 情报杂志, 2017, 36(8):81-87.
|
| [4] |
MARTIN L, PU P. Prediction of helpful reviews using emotions extraction[C]// Twenty-Eighth AAAI conference on artificial intelligence. Palo Alto: AAAI Press, 2014:1551-1557.
|
| [5] |
FELBERMAYR A, NANOPOULOS A. The role of emotions for the perceived usefulness in online customer reviews[J]. Journal of interactive marketing, 2016, 36(11):60-76.
|
| [6] |
YIN D, BOND S D, ZHANG H. Anxious or angry? effects of discrete emotions on the perceived helpfulness of online reviews[J]. MIS auarterly, 2014, 38(2): 539-560.
|
| [7] |
史伟, 王洪伟, 何绍义. 基于语义的中文在线评论情感分析[J]. 情报学报, 2013, 32(8):860-867.
|
| [8] |
聂卉. 隐主题模型下产品评论观点的凝聚与量化[J]. 情报学报, 2017, 36(6):565-573.
|
| [9] |
金燕. 基于情绪分析的UGC质量评判模型[J]. 图书情报工作, 2017, 61(20):131-139.
|
| [10] |
BAGOZZI R, GOPINATH M, NYER P U. The role of emotions in marketing[J]. Journal of the academy of marketing science, 1999, 24(3):149-167.
|
| [11] |
ULLAH R, AMBLEE N, KIM W, et al. From valence to emotions: exploring the distribution of emotions in online product reviews[J]. Decision support systems, 2016, 81(5):41-53.
|
| [12] |
EKMAN P. An argument for basic emotions[J]. Cognition & emotion, 1992, 6(3/4):169-200.
|
| [13] |
曹宇, 王名扬, 贺惠新. 情感词典扩充的微博文本多元情感分类研究[J]. 情报杂志, 2016, 35(10):185-189.
|
| [14] |
MUDAMBI S M, SCHUFF D. What makes a helpful online review? a study of customer reviews on amazon.com[J]. Social science electronic publishing, 2010, 34(1):185-200.
|
| [15] |
GHOSE A, IPEIROTIS P G. Estimating the helpfulness and economic impact of product reviews: mining text and reviewer characteristics[J]. Social science electronic publishing, 2010, 23(10):1498-1512.
|
| [16] |
LEE J H, SUN H J, PARK J H. The role of entropy of review text sentiments on online WOM and movie box office sales[M]. New York:Elsevier Science Publishers B. V. ,2017.
|
| [17] |
KO M, KIM H W, YI M Y, et al. MovieCommenter: Aspect-based collaborative filtering by utilizing user comments[C]// International conference on collaborative computing: networking, applications and worksharing. Piscataway :IEEE, 2012:362-371.
|
| [18] |
殷国鹏, 刘雯雯, 祝珊. 网络社区在线评论有用性影响模型研究——基于信息采纳与社会网络视角[J]. 图书情报工作, 2012,56(16): 140-147.
|
| [19] |
薛博召. 图书领域消费者在线评论的有用性影响因素研究[D]. 哈尔滨:哈尔滨工业大学,2011.
|
| [20] |
张丽, 张蕾, 张阳, 等. 基于中文分词和词频统计的图书在线评论文本分析[J]. 信息系统工程, 2011(7):71-73.
|
| [21] |
祝振媛. 基于信息分类的网络书评内容挖掘与整合研究[J]. 图书情报工作, 2016,60(1):114-124.
|
| [22] |
LIU B. Sentiment analysis and opinion mining[J]. Synthesis lectures on human language technologies, 2012, 5(1): 1-167.
|
| [23] |
CARD S K, MACKINLAY J D, SHNEIDERMAN B. Readings in information visualization - using vision to think[C]// Series in interactive technologies. San Francisco:Morgan Kaufmann Publishers Inc.,1999.
|
| [24] |
SIEVERT C, SHIRLEY K E. LDAvis:A method for visualizing and interpreting topics[EB/OL].[2018-01-23].https://www.researchgate.net/publication/265784473_LDAvis_A_method_for_visualizing_and_interpreting_topics.
|
| [25] |
胡吉明, 陈果. 基于动态LDA主题模型的内容主题挖掘与演化[J]. 图书情报工作, 2014, 58(2):138-142.
|
/
| 〈 |
|
〉 |