检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
出 处:《计算机应用与软件》2016年第7期114-117,133,共5页Computer Applications and Software
摘 要:为了更好地对微博进行表示,提高微博情感倾向性识别的准确度,提出一种基于Skip-gram模型的微博情感倾向性分析方法。首先,使用Skip-gram模型在中文数据上进行训练得到词向量;然后,利用词向量在词语表示上的优势,以及一定程度上满足加法组合运算的特性,通过向量相加获得微博的向量表示以及正负情感向量;最后,通过计算微博向量和正负情感向量的相似度判断微博的情感倾向。在NLP&CC2012数据上进行实验,结果表明,该方法能够有效识别微博的情感倾向,较传统的JST(Joint Sentiment/Topic model)和ASUM(Aspect and Sentiment Unication Model)平均F1值分别提高了23%和26%。In order to represent microblogs better and to improve the accuracy of microblogging sentiment orientation identification,we presented a Skip-gram model-based microblogging sentiment orientation analysis method. First,we used Skip-gram model in training on Chinese dataset to get word vector; then,we took use of the advantage of word vector on word representation and its feature of satisfying in certain extent the addition combinational operation to obtain the vector representation of microblogs and the positive and negative sentiment vectors by vectors addition; finally,we determined the microblogging sentiment orientation by computing the similarity between microblogging vectors and positive and negative sentiment vectors. Experiment was carried out on NLP&CC2012 data,the results showed that our method could effectively identify the sentiment orientation of microblogs,and improved the average F1-measure by 23% and 26% respectively compared with traditional JST and ASUM.
关 键 词:微博 情感分析 Skip-gram 模型 词向量 微博向量
分 类 号:TP391.4[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.222