本文關(guān)鍵詞：社交媒體文本情感分析　出處：《南京理工大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 社交媒體 情感分類 語義規(guī)則 融合方法 情感詞典 集成學(xué)習(xí)

【摘要】：近年來互聯(lián)網(wǎng)技術(shù)依然保持著高速的發(fā)展?fàn)顟B(tài),涌現(xiàn)了大量的互聯(lián)網(wǎng)應(yīng)用,包括社交網(wǎng)絡(luò)應(yīng)用�；ヂ�(lián)網(wǎng)上時刻產(chǎn)生著大量用戶參與的人物、產(chǎn)品、事件等相關(guān)的社交媒體數(shù)據(jù)。情感分析技術(shù)用于挖掘文本中的主觀情感信息,對微博為代表的社交媒體的情感分析可以挖掘其中潛在的商業(yè)與社會價值,在產(chǎn)品信息反饋、商品推薦算法、輿情監(jiān)控、熱點事件跟蹤等方面有重要應(yīng)用。本文主要研究面向社交媒體的情感分類問題,前兩章對該問題的研究現(xiàn)狀和基本技術(shù)進(jìn)行了詳細(xì)的介紹。然后,從不同的角度針對現(xiàn)有研究的不足之處,在第三至五章分別提出了本文的情感分類方法。(1)提出了一種機器學(xué)習(xí)與語義規(guī)則融合的情感分類方法。本文針對中文微博特點,在傳統(tǒng)的基于詞典分類方法上添加了多項語義規(guī)則,提高了對樣本情感傾向度衡量的精準(zhǔn)度。然后提出了特征嵌入式的融合方法,即將提取的詞典規(guī)則特征轉(zhuǎn)化擴展以后加入基本特征模板,該融合方式在情感分析粒度和特征表示兩個方面優(yōu)于一般的融合方法。實驗證明該方法取得了較大的性能提升,在2015年的中文傾向性評測(COAE2015)的微博情感分類任務(wù)中,取得了限定資源模式下的第一名。(2)本文面向社交媒體數(shù)據(jù),借助自然標(biāo)注的方法幫助解決情感分類問題。在第4章,本文以神經(jīng)網(wǎng)絡(luò)模型詞典構(gòu)建方法為基礎(chǔ),通過加入語義規(guī)則和設(shè)置樣本權(quán)重的方式對其進(jìn)行了改進(jìn)。在與人工標(biāo)注詞典和其他詞典學(xué)習(xí)算法的比較中,該方法學(xué)習(xí)出的詞典表現(xiàn)最優(yōu)。使用該詞典在2016年的中文傾向性評測(COAE2016)的情感詞抽取任務(wù)中,取得了第一名的成績。(3)本文提出在自然標(biāo)注數(shù)據(jù)上進(jìn)行集成學(xué)習(xí)提高分類性能。首先實驗驗證了Bagging集成模型相比于單一模型在穩(wěn)定性和泛化能力上的優(yōu)越性。在此基礎(chǔ)上,提出Stacking集成學(xué)習(xí)模型,該模型通過對多個基分類器預(yù)測結(jié)果的二次學(xué)習(xí),以及原有的詞典特征,實現(xiàn)了自然標(biāo)注數(shù)據(jù)和人工標(biāo)注數(shù)據(jù)的全面結(jié)合。實驗證明,該模型的分類性能高于僅加入詞典特征的結(jié)合方式。
[Abstract]:In recent years, Internet technology still maintains a high-speed state of development, a large number of Internet applications have emerged, including social network applications. Event and other related social media data. Emotional analysis technology is used to mine the subjective emotional information in the text. The emotional analysis of social media represented by Weibo can tap the potential commercial and social value. It has important applications in product information feedback, product recommendation algorithm, public opinion monitoring, hot event tracking and so on. The first two chapters introduce the current situation and basic technology of this problem in detail. Then, from different angles, the shortcomings of the existing research are pointed out. In the third to fifth chapters, we put forward the emotion classification method of this paper respectively. (1) proposed a kind of emotion classification method which combines machine learning and semantic rules. This paper aims at the characteristics of Chinese micro-blog. Several semantic rules are added to the traditional dictionary-based classification method, which improves the accuracy of the measurement of sample emotional tendency. Then, a feature embedded fusion method is proposed. After the feature transformation of the extracted dictionary rules is extended, the basic feature template is added. The fusion method is superior to the general fusion method in terms of emotion analysis granularity and feature representation. In 2015, the Chinese tendentiousness Evaluation (COAE2015) of the Weibo emotional classification task, obtained a limited resource model under the first.) this paper is oriented to social media data. In Chapter 4, this paper is based on the neural network model dictionary construction method. It is improved by adding semantic rules and setting the weight of samples, which is compared with the learning algorithms of manual annotated dictionaries and other dictionaries. The best performance of the dictionary was obtained by this method. The dictionary was used in the affective word extraction task of COAE2016, a Chinese tendentiousness evaluation in 2016. First place score. In this paper, ensemble learning based on natural tagging data is proposed to improve classification performance. Firstly, the superiority of Bagging integration model compared with single model in stability and generalization ability is verified by experiments. . Stacking integrated learning model is proposed. The model is based on the quadratic learning of the prediction results of multiple base classifiers and the original dictionary features. The combination of natural tagged data and manual tagged data is realized. The experimental results show that the classification performance of the model is better than that of only adding dictionary features.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 張志琳;宗成慶;;基于多樣化特征的中文微博情感分類方法研究[J];中文信息學(xué)報;2015年04期

2 周紅照;侯明午;顏彭莉;張葉青;侯敏;滕永林;;語義特征在評價對象抽取與極性判定中的作用[J];北京大學(xué)學(xué)報(自然科學(xué)版);2014年01期

3 龐磊;李壽山;周國棟;;基于情緒知識的中文微博情感分類方法[J];計算機工程;2012年13期

4 陳堅永;羅鎮(zhèn)川;鄧燕玲;張圭煜;;Phrase-Level Sentiment Polarity Classification Using Rule-Based Typed Dependencies and Additional Complex Phrases Consideration[J];Journal of Computer Science & Technology;2012年03期

5 謝麗星;周明;孫茂松;;基于層次結(jié)構(gòu)的多策略中文微博情感分析和特征抽取[J];中文信息學(xué)報;2012年01期

6 代六玲,黃河燕,陳肇雄;中文文本分類中特征抽取方法的比較研究[J];中文信息學(xué)報;2004年01期

，

本文編號：1412536