本文選題：細(xì)粒度情感分析 + 長(zhǎng)短期記憶網(wǎng)絡(luò)��； 參考：《哈爾濱工業(yè)大學(xué)》2017年碩士論文

【摘要】：隨著互聯(lián)網(wǎng)電商平臺(tái)的不斷發(fā)展,網(wǎng)絡(luò)購(gòu)物逐漸成為越來(lái)越多網(wǎng)民的購(gòu)物方式。與此同時(shí),網(wǎng)絡(luò)上針對(duì)產(chǎn)品的大量評(píng)論也隨之涌現(xiàn),這些評(píng)論既成為了網(wǎng)民購(gòu)物時(shí)的參考,也為廠商了解用戶反饋提供了便利的條件。不過(guò),大規(guī)模的評(píng)論無(wú)法全部進(jìn)行人工審閱,導(dǎo)致用戶和廠商無(wú)法全面了解一款產(chǎn)品的大眾評(píng)價(jià)。受益于計(jì)算機(jī)處理能力的增長(zhǎng)和大數(shù)據(jù)時(shí)代的來(lái)臨,自然語(yǔ)言處理技術(shù)作為人工智能重要的研究與應(yīng)用領(lǐng)域,已經(jīng)在諸多領(lǐng)域發(fā)揮了不可替代的作用。計(jì)算機(jī)擁有處理大規(guī)模數(shù)據(jù)的能力,同時(shí)成本低、效率高,如果計(jì)算機(jī)能夠自動(dòng)幫助用戶和廠商分析產(chǎn)品評(píng)論中用戶所表達(dá)的態(tài)度,將節(jié)省大量的人力物力。文本情感分析是自然語(yǔ)言領(lǐng)域中非常重要的研究方向之一。文本情感分析算法能夠自動(dòng)從篇章或句子中分析出用戶的態(tài)度,比如支持、反對(duì)、或是中性;甚至能夠分析出用戶的情緒,比如喜悅、悲傷、驚奇等。但是,篇章級(jí)別與句子級(jí)別的情感分析通常無(wú)法找到用戶所表達(dá)的態(tài)度的對(duì)象。在對(duì)產(chǎn)品評(píng)論的分析中,我們不僅對(duì)用戶的態(tài)度感興趣,更想了解用戶對(duì)產(chǎn)品的哪一方面表達(dá)出了肯定或不滿的態(tài)度。細(xì)粒度情感分析則能夠很好地解決這個(gè)問(wèn)題,找出用戶評(píng)論中的評(píng)價(jià)對(duì)象與評(píng)價(jià)詞、并確定它們之間的搭配關(guān)系是細(xì)粒度情感分析最重要的步驟。本文首先探究了基于循環(huán)神經(jīng)網(wǎng)絡(luò)的序列標(biāo)注方法。這一方法將評(píng)價(jià)對(duì)象和評(píng)價(jià)詞的提取工作看作是序列標(biāo)注任務(wù),通過(guò)對(duì)句子中每一個(gè)詞語(yǔ)打標(biāo)簽的方式,確定哪些詞語(yǔ)是評(píng)價(jià)對(duì)象,哪些詞語(yǔ)是評(píng)價(jià)詞。此外,還需要確定評(píng)價(jià)對(duì)象與評(píng)價(jià)詞之間的搭配關(guān)系。本文使用了兩種關(guān)系分類的方法,分別為基于句法與語(yǔ)義信息核函數(shù)的分類方法和基于融合句法關(guān)系的神經(jīng)網(wǎng)絡(luò)的分類方法。這兩種方法均與句法關(guān)系相結(jié)合,充分利用詞與詞之間的句法關(guān)系,確定出兩個(gè)詞之間是否為正確的搭配關(guān)系,進(jìn)而對(duì)評(píng)價(jià)對(duì)象和評(píng)價(jià)詞進(jìn)行抽取。實(shí)驗(yàn)結(jié)果表明,三種算法在各自的任務(wù)上均非常有效。在詞語(yǔ)抽取的任務(wù)上,基于循環(huán)神經(jīng)網(wǎng)絡(luò)的序列標(biāo)注方法要優(yōu)于基于規(guī)則的詞語(yǔ)抽取算法。在搭配關(guān)系抽取的任務(wù)上,融合了句法結(jié)構(gòu)信息的模型的性能得到了明顯的提高,說(shuō)明了句法結(jié)構(gòu)在關(guān)系分類任務(wù)上的有效性。同時(shí),基于卷積神經(jīng)網(wǎng)絡(luò)與遞歸神經(jīng)網(wǎng)絡(luò)的混合模型能夠更好地對(duì)句子的語(yǔ)義信息進(jìn)行建模,性能更加突出。
[Abstract]:With the continuous development of the Internet e-commerce platform, online shopping has gradually become more and more Internet users' shopping. At the same time, a large number of comments on the products have emerged on the Internet. These comments have not only become the reference of the Internet users, but also provide the convenience for the manufacturers to understand the feedback of the users. All the methods of manual review have led to the failure of users and manufacturers to fully understand the public evaluation of a product. Benefiting from the growth of computer processing capacity and the coming of the era of large data, Natural Language Processing technology has played an irreplaceable role in many fields as an important research and application field of artificial intelligence. It has the ability to process large-scale data with low cost and high efficiency. If the computer can automatically help users and vendors to analyze the attitude expressed by users in the product reviews, it will save a lot of manpower and material resources. Text emotion analysis is one of the most important research directions in the field of natural language. A user's attitude, such as support, opposition, or neutrality, is analyzed from a text or sentence, such as the emotion of the user, such as joy, sadness, surprise, etc., but the emotional analysis of the text level and the sentence level is usually unable to find the object of the user's attitude. In the analysis of the product review, we are not only to the user. The attitude of the user is more interested in understanding which aspect of the product is positive or dissatisfied. Fine-grained emotion analysis can solve the problem well, find the evaluation objects and evaluation words in the user reviews, and determine the collocation relationship between them is the most important step in the fine granularity emotional analysis. The method of sequence Tagging Based on recurrent neural network is studied. This method regards the extraction of evaluation objects and evaluation words as sequence tagging tasks. By labeling each word in the sentence, it determines which words are evaluation objects and which words are evaluation words. In addition, it is necessary to determine the relationship between the evaluation object and the evaluation word. Two kinds of relationship classification methods are used in this paper, the classification method based on syntactic and semantic information kernel function and the classification method of neural network based on syntactic relations. These two methods are combined with syntactic relations, make full use of the syntactic relationship between words and words, and determine whether the two words are positive or not. The experimental results show that the three algorithms are very effective on their respective tasks. On the task of word extraction, the sequence tagging method based on recurrent neural network is superior to the rule based word extraction algorithm. The syntax is syntactically integrated on the task of the collocation relationship extraction. The performance of the structure information model has been greatly improved, which shows the validity of the syntactic structure in the relationship classification task. At the same time, the hybrid model based on the convolution neural network and the recurrent neural network can better model the semantic information of the sentence, and the performance is more outburst.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 趙妍妍;秦兵;劉挺;;文本情感分析[J];軟件學(xué)報(bào);2010年08期

，

本文編號(hào)：1967586