本文選題：情感分析 + 極性分類(lèi)��； 參考：《浙江大學(xué)》2017年碩士論文

【摘要】：隨著國(guó)務(wù)院總理李克強(qiáng)在政府報(bào)告工作中對(duì)"互聯(lián)網(wǎng)+"概念的提出,目前傳統(tǒng)行業(yè)正在尋求突破與創(chuàng)新,將自身主營(yíng)業(yè)務(wù)與互聯(lián)網(wǎng)結(jié)合起來(lái),實(shí)現(xiàn)企業(yè)再創(chuàng)造的價(jià)值邊際效應(yīng)。作為傳統(tǒng)行業(yè)的公交產(chǎn)業(yè),也希望能通過(guò)互聯(lián)網(wǎng)、大數(shù)據(jù)平臺(tái)等工具對(duì)流量、輿情信息進(jìn)行智能的采集與梳理,優(yōu)化目前公交產(chǎn)業(yè)的一些問(wèn)題。因此,基于人工智能的情感分析在其中扮演了重要的角色。目前,情感分析的研究已經(jīng)相對(duì)比較成熟,但現(xiàn)有情感分析技術(shù)在實(shí)際行業(yè)應(yīng)用中多采用基于監(jiān)督的方式,這種方法正確率較高,但移植性較低,并且人力成本高。而基于無(wú)監(jiān)督方式的情感分析精度雖然有所降低,但卻能彌補(bǔ)以上不足,他能減少在數(shù)據(jù)量較少情況下建模的不準(zhǔn)確性,并且快速應(yīng)用于新的領(lǐng)域并展現(xiàn)出較好的效果。因此,本文基于公交輿情的特點(diǎn)對(duì)原有的基于無(wú)監(jiān)督的情感分析技術(shù)進(jìn)行了研究與改進(jìn),具體的研究工作包括以下幾方面:1.提出了基于Word2Vec的情感詞典擴(kuò)建方法,結(jié)合詞語(yǔ)的領(lǐng)域性和語(yǔ)義信息后盡可能多的覆蓋使用率較高的情感詞匯。2.建立了新的適于長(zhǎng)文本的文本表示模型——RPFLO模型,實(shí)現(xiàn)了情感詞與其評(píng)價(jià)對(duì)象的對(duì)應(yīng)關(guān)系,揭示了長(zhǎng)文本中句子順序和隱藏在句子間的語(yǔ)義關(guān)系。3.提出了基于RPFLO模型的事件主體抽取方法,該方法利用公共子串自動(dòng)化抽取初始簇中心來(lái)改進(jìn)K-means聚類(lèi)算法。4.提出了基于改進(jìn)的Cure算法的相似話題聚類(lèi)方法。首先對(duì)離群點(diǎn)預(yù)處理,其次引入不可達(dá)類(lèi),實(shí)現(xiàn)了傳統(tǒng)聚類(lèi)算法無(wú)法實(shí)現(xiàn)的過(guò)程自動(dòng)終止功能,提高算法的效率。通過(guò)研究改進(jìn),本論文實(shí)現(xiàn)了無(wú)監(jiān)督情感分析模式的優(yōu)化,在保證高移植性和低人力成本的基礎(chǔ)上大幅提高分析精度。
[Abstract]:With Premier Li Keqiang of the State Council putting forward the concept of "Internet" in the government report, at present, traditional industries are seeking to break through and innovate, combining their main business with the Internet. To realize the marginal value effect of enterprise re-creation. As a traditional industry, the public transport industry also hopes to use the Internet, big data platform and other tools to intelligently collect and comb the information of traffic and public opinion, and optimize some problems of the current public transport industry. Therefore, the emotional analysis based on artificial intelligence plays an important role in it. At present, the research of affective analysis has been relatively mature, but the existing affective analysis technology is mostly based on supervision in the application of the actual industry, this method has a high correct rate, but low portability, and high labor cost. Although the accuracy of emotion analysis based on unsupervised method is reduced, it can make up for the above shortcomings. It can reduce the inaccuracy of modeling in the case of less data, and quickly apply it to new fields and show better results. Therefore, based on the characteristics of public opinion, this paper studies and improves the original unsupervised emotion analysis technology. The specific research work includes the following aspects: 1. This paper proposes an extension method of affective dictionary based on Word2Vec, which covers as many affective words as possible after combining the domain and semantic information of words. A new text representation model suitable for long text, RPFLO model, is established. The corresponding relationship between emotional words and their evaluation objects is realized, and the sentence order and the semantic relationship between sentences hidden in long text are revealed. In this paper, an event subject extraction method based on RPFLO model is proposed. The method uses common substring to automatically extract the initial cluster center to improve the K-means clustering algorithm .4. A similar topic clustering method based on improved Cure algorithm is proposed. Firstly, the outlier is pretreated, and then the unreachable class is introduced to realize the function of automatic process termination which can not be realized by the traditional clustering algorithm, so as to improve the efficiency of the algorithm. Through research and improvement, this paper realizes the optimization of unsupervised emotional analysis mode, and improves the precision of analysis on the basis of ensuring high portability and low labor cost.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳玉琢;;“互聯(lián)網(wǎng)+”經(jīng)濟(jì)模式下新媒體從業(yè)人員統(tǒng)戰(zhàn)工作創(chuàng)新研究[J];湖北函授大學(xué)學(xué)報(bào);2016年23期

2 相若晨;孫美鳳;;基于詞向量與句法樹(shù)的中文句子情感分析[J];計(jì)算機(jī)與現(xiàn)代化;2016年08期

3 ;看點(diǎn)!第38次《中國(guó)互聯(lián)網(wǎng)絡(luò)發(fā)展?fàn)顩r統(tǒng)計(jì)報(bào)告》[J];科學(xué)家;2016年09期

4 李天彩;王波;毛二松;席耀一;;基于Skip-gram模型的微博情感傾向性分析[J];計(jì)算機(jī)應(yīng)用與軟件;2016年07期

5 蘇瑩;張勇;胡珀;涂新輝;;基于樸素貝葉斯與潛在狄利克雷分布相結(jié)合的情感分析[J];計(jì)算機(jī)應(yīng)用;2016年06期

6 伊馬木·達(dá)吾提;何炎祥;劉續(xù)樂(lè);;基于主謂情感差異性句法分析框架的跨語(yǔ)言情感分析[J];小型微型計(jì)算機(jī)系統(tǒng);2016年03期

7 陳夏芳;曹春萍;;改進(jìn)的譜聚類(lèi)算法在文本情感分析中的應(yīng)用[J];信息技術(shù);2015年12期

8 杜銳;朱艷輝;田海龍;劉t，

本文編號(hào)：1821030