54
个编辑
更改
跳到导航
跳到搜索
第455行：
第455行： − + − + − − 第468行：
第466行： − + 第478行：
第476行： − + − − − 开源软件工具以及一系列免费和付费的情绪分析工具利用机器学习、统计学和自然语言处理技术，对大量文本自动进行情绪分析，这些文本包括网页、在线新闻、互联网讨论组、在线评论、网络博客和社交媒体。另一方面，知识推理系统则利用公开的资源，提取与自然语言概念相关的语义和情感信息。该系统可以帮助执行情感常识推理。情感分析也可以在可视内容上执行，例如，图像和视频(请参阅 Multimodal 情感分析)。这方面的第一个方法是使用形容词名词对表示视觉内容。此外，绝大多数情感分类方法都依赖于情感分类词袋模型，它忽略了上下文、语法甚至词序。基于词语组成长短语意义的情感分析方法取得了较好的效果，但也增加了额外的注释开销。+ − 在情感分析中需要一个人工分析组件，因为自动化系统不能分析个人评论者或平台的历史趋势，而且在他们表达的情感中常常被错误地分类。自动化影响了大约23% 被人类正确分类的评论。然而，人们往往不同意，并认为人际协议提供了一个上限，自动情绪分类器最终可以达到。+
→Methods and features方法和特征
</ref>
</ref>
现有的情感分析的方法主要可以分成三类：基于知识的技术（knowledge-based techniques）、统计方法（statistical methods）和混合方法（hybrid approaches）。<ref name="“Cambria" /> 基于知识的技术根据明确的情感词（如快乐、悲伤、害怕和无聊）的存在对文本进行分类。<ref name="Ortony" /> 一些知识库不仅列出了明显的情感，而且还赋予了任意词汇与特定情感可能的“亲和性”。<ref name="Stevenson" /> 统计方法通过调控机器学习中的元素，比如潜在语意分析（latent semantic analysis），SVM（support vector machines），词袋（bag of words），（Pointwise Mutual Information for Semantic Orientation）和深度学习（depp learning）等等。一些复杂的方法意在检测出情感持有者（比如，保持情绪状态的那个人）和情感目标（比如，让情感持有者产生情绪的实体）。<ref name="Kim+Hovy06" /> 语法依赖关系是通过对文本的深度解析得到的。<ref name="DeyHaque08" /> 与单纯的语义技术不同的是，混合算法的思路利用了知识表达（knowledge representation）的元素，比如知识本体 （ontologies）、语意网络（semantic networks），因此这种算法也可以检测到文字间比较微妙的情感表达。例如， 通过分析一些没有明确表达相关信息的概念与明确概念的隐性的联系来获取所求信息。<ref name="“Hussain" />要想挖掘在某语境下的意见，或是获取被给予意见的某项功能，需要使用到语法之间的关系。语法之间互相的关联性经常需要通过深度解析文本来获取。'''<u>【翻译到这里】</u>'''
现有的情感分析的方法主要可以分成三类：基于知识的技术（knowledge-based techniques）、统计方法（statistical methods）和混合方法（hybrid approaches）。<ref name="“Cambria" /> 基于知识的技术根据明确的情感词（如快乐、悲伤、害怕和无聊）的存在对文本进行分类。<ref name="Ortony" /> 一些知识库不仅列出了明显的情感，而且还赋予了任意词汇与特定情感可能的“亲和性”。<ref name="Stevenson" /> 统计方法通过调控机器学习中的元素，比如潜在语意分析（latent semantic analysis），SVM（support vector machines），词袋（bag of words），（Pointwise Mutual Information for Semantic Orientation）和深度学习（depp learning）等等。一些复杂的方法意在检测出情感持有者（比如，保持情绪状态的那个人）和情感目标（比如，让情感持有者产生情绪的实体）。<ref name="Kim+Hovy06" /> 语法依赖关系是通过对文本的深度解析得到的。<ref name="DeyHaque08" /> 与单纯的语义技术不同的是，混合算法的思路利用了知识表达（knowledge representation）的元素，比如知识本体 （ontologies）、语意网络（semantic networks），因此这种算法也可以检测到文字间比较微妙的情感表达。例如， 通过分析一些没有明确表达相关信息的概念与明确概念的隐性的联系来获取所求信息。<ref name="“Hussain" />要想挖掘在某语境下的意见，或是获取被给予意见的某项功能，需要使用到语法之间的关系。语法之间互相的关联性经常需要通过深度解析文本来获取。
Open source software tools as well as range of free and paid sentiment analysis tools deploy [[machine learning]], statistics, and natural language processing techniques to automate sentiment analysis on large collections of texts, including web pages, online news, internet discussion groups, online reviews, web blogs, and social media.<ref name="AkcoraBayirDemirbasFerhatosmanoglu2010">
Open source software tools as well as range of free and paid sentiment analysis tools deploy [[machine learning]], statistics, and natural language processing techniques to automate sentiment analysis on large collections of texts, including web pages, online news, internet discussion groups, online reviews, web blogs, and social media.有很多开源软件使用机器学习（machine learning）、统计、自然语言处理的技术来计算大型文本集的情感分析, 这些大型文本集合包括网页、网络新闻、网上讨论群、网络评论、博客和社交媒介。<ref name="AkcoraBayirDemirbasFerhatosmanoglu2010">
{{cite conference
{{cite conference
| first1 = Cuneyt Gurcan | last1 = Akcora | first2 = Murat Ali | last2 = Bayir | first3 = Murat | last3 = Demirbas | first4 = Hakan | last4 = Ferhatosmanoglu
| first1 = Cuneyt Gurcan | last1 = Akcora | first2 = Murat Ali | last2 = Bayir | first3 = Murat | last3 = Demirbas | first4 = Hakan | last4 = Ferhatosmanoglu
| url = http://portal.acm.org/citation.cfm?id=1964867
| url = http://portal.acm.org/citation.cfm?id=1964867
}}
}}
</ref> Knowledge-based systems, on the other hand, make use of publicly available resources, to extract the semantic and affective information associated with natural language concepts. The system can help perform affective [[commonsense reasoning]].<ref>{{Cite journal|last1=Sasikala|first1=P.|last2=Mary Immaculate Sheela|first2=L.|date=December 2020|title=Sentiment analysis of online product reviews using DLMNN and future prediction of online product using IANFIS|journal=Journal of Big Data|language=en|volume=7|issue=1|pages=33|doi=10.1186/s40537-020-00308-7|issn=2196-1115|doi-access=free}}</ref> Sentiment analysis can also be performed on visual content, i.e., images and videos (see [[Multimodal sentiment analysis]]). One of the first approaches in this direction is SentiBank<ref name = "Borth13">
</ref> Knowledge-based systems, on the other hand, make use of publicly available resources, to extract the semantic and affective information associated with natural language concepts. The system can help perform affective [[commonsense reasoning]].<ref name=":24">{{Cite journal|last1=Sasikala|first1=P.|last2=Mary Immaculate Sheela|first2=L.|date=December 2020|title=Sentiment analysis of online product reviews using DLMNN and future prediction of online product using IANFIS|journal=Journal of Big Data|language=en|volume=7|issue=1|pages=33|doi=10.1186/s40537-020-00308-7|issn=2196-1115|doi-access=free}}</ref> Sentiment analysis can also be performed on visual content, i.e., images and videos (see [[Multimodal sentiment analysis]]). One of the first approaches in this direction is SentiBank<ref name="Borth13">
{{cite conference
{{cite conference
| first1 = Damian | last1 = Borth
| first1 = Damian | last1 = Borth
| url = https://visual-sentiment-ontology.appspot.com
| url = https://visual-sentiment-ontology.appspot.com
}}
}}
</ref> utilizing an adjective noun pair representation of visual content. In addition, the vast majority of sentiment classification approaches rely on the bag-of-words model, which disregards context, [[grammar]] and even [[word order]]. Approaches that analyses the sentiment based on how words compose the meaning of longer phrases have shown better result,<ref>{{Cite journal|last1=Socher|first1=Richard|last2=Perelygin|first2=Alex|last3=Wu|first3=Jean Y.|last4=Chuang|first4=Jason|last5=Manning|first5=Christopher D.|last6=Ng|first6=Andrew Y.|last7=Potts|first7=Christopher|date=2013|title=Recursive deep models for semantic compositionality over a sentiment treebank|journal=In Proceedings of EMNLP|pages=1631–1642|citeseerx=10.1.1.593.7427}}</ref> but they incur an additional annotation overhead.
</ref> utilizing an adjective noun pair representation of visual content. In addition, the vast majority of sentiment classification approaches rely on the bag-of-words model, which disregards context, [[grammar]] and even [[word order]]. Approaches that analyses the sentiment based on how words compose the meaning of longer phrases have shown better result,<ref name=":25">{{Cite journal|last1=Socher|first1=Richard|last2=Perelygin|first2=Alex|last3=Wu|first3=Jean Y.|last4=Chuang|first4=Jason|last5=Manning|first5=Christopher D.|last6=Ng|first6=Andrew Y.|last7=Potts|first7=Christopher|date=2013|title=Recursive deep models for semantic compositionality over a sentiment treebank|journal=In Proceedings of EMNLP|pages=1631–1642|citeseerx=10.1.1.593.7427}}</ref> but they incur an additional annotation overhead.
有很多开源软件工具以及一系列免费和付费的情感分析工具利用机器学习、统计学方法和自然语言处理的技术，对大型文本语料进行情感分析, 这些大型文本语料包括网页、网络新闻、互联网在线讨论群组、网络在线评论、网络博客和社交媒介。<ref name="AkcoraBayirDemirbasFerhatosmanoglu2010" /> 另一方面，基于知识的系统利用公开可用的资源，提取与自然语言概念相关的语义和情感信息。该系统可以帮助执行情感常识推理。<ref name=":24" /> 此外，情感分析也可以在视觉内容层面上进行，例如多模态情感分析（multimodal sentiment analysis）中对图像和视频进行分析。这方面的第一种方法是SentiBank。<ref name="Borth13" /> SentiBank方法利用形容词-名词对来代表视觉内容的属性。另外，绝大多数的情感分类方法都依赖于词袋模型（bag-of-words model），它忽略上下文语境、语法甚至是语序。根据词语如何构成较长短语的意义来分析情感的方法显示出了更好的效果，<ref name=":25" /> 但它们会也会导致产生额外的标识成本。
A human analysis component is required in sentiment analysis, as automated systems are not able to analyze historical tendencies of the individual commenter, or the platform and are often classified incorrectly in their expressed sentiment. Automation impacts approximately 23% of comments that are correctly classified by humans.<ref>{{cite web|title=Case Study: Advanced Sentiment Analysis|url=http://paragonpoll.com/sentiment-analysis-systems-case-study/|access-date=18 October 2013}}</ref> However, humans often disagree, and it is argued that the inter-human agreement provides an upper bound that automated sentiment classifiers can eventually reach.<ref>{{Cite journal|last1=Mozetič|first1=Igor|last2=Grčar|first2=Miha|last3=Smailović|first3=Jasmina|date=2016-05-05|title=Multilingual Twitter Sentiment Classification: The Role of Human Annotators|journal=PLOS ONE|volume=11|issue=5|pages=e0155036|doi=10.1371/journal.pone.0155036|issn=1932-6203|pmc=4858191|pmid=27149621|arxiv=1602.07563|bibcode=2016PLoSO..1155036M}}</ref>
A human analysis component is required in sentiment analysis, as automated systems are not able to analyze historical tendencies of the individual commenter, or the platform and are often classified incorrectly in their expressed sentiment. Automation impacts approximately 23% of comments that are correctly classified by humans.<ref>{{cite web|title=Case Study: Advanced Sentiment Analysis|url=http://paragonpoll.com/sentiment-analysis-systems-case-study/|access-date=18 October 2013}}</ref> However, humans often disagree, and it is argued that the inter-human agreement provides an upper bound that automated sentiment classifiers can eventually reach.<ref>{{Cite journal|last1=Mozetič|first1=Igor|last2=Grčar|first2=Miha|last3=Smailović|first3=Jasmina|date=2016-05-05|title=Multilingual Twitter Sentiment Classification: The Role of Human Annotators|journal=PLOS ONE|volume=11|issue=5|pages=e0155036|doi=10.1371/journal.pone.0155036|issn=1932-6203|pmc=4858191|pmid=27149621|arxiv=1602.07563|bibcode=2016PLoSO..1155036M}}</ref>
在情感分析中，需要有人工分析的成分。因为自动化系统无法分析评论者个人的历史倾向，也无法分析平台的历史倾向，这往往导致对表达的情感的错误分类。自动化情感分类器通常能够识别大约23% 被人类正确分类的评论。然而，人们往往不同意这种说法，。并认为人与人之间的一致意见提供了一个自动化情感分类器最终可以达到的上限
== Evaluation 评估 ==
== Evaluation 评估 ==