[1]唐宇坤,邓 松*,唐熙淳,等.基于矛盾关系的评教文本反语检测算法[J].江西师范大学学报(自然科学版),2022,(01):59-66.[doi:10.16357/j.cnki.issn1000-5862.2022.01.08]
　TANG Yukun,DENG Song*,TANG Xichun,et al.The Irony Detection Algorithm of Student's Teaching Evaluation Data Based on Contradiction[J].Journal of Jiangxi Normal University:Natural Science Edition,2022,(01):59-66.[doi:10.16357/j.cnki.issn1000-5862.2022.01.08]
点击复制

基于矛盾关系的评教文本反语检测算法()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2022年01期
页码:
59-66
栏目:
信息科学与技术
出版日期:
2022-01-25

文章信息/Info

Title:
The Irony Detection Algorithm of Student's Teaching Evaluation Data Based on Contradiction
文章编号:
1000-5862(2022)01-0059-08
作者:
唐宇坤; 邓 松*; 唐熙淳; 许梦雅; 郭 馨
江西财经大学软件与物联网工程学院,江西 南昌 330013
Author(s):
TANG Yukun; DENG Song*; TANG Xichun; XU Mengya; GUO Xin
1.School of Software and Internet of Things Engineering,Jiangxi University of Finance and Economics,Nanchang Jiangxi 330013,China
关键词:
学生评教;  语义分析;  反语识别
Keywords:
teaching evaluation of student;  semantic analysis;  irony recognition
分类号:
TP 311
DOI:
10.16357/j.cnki.issn1000-5862.2022.01.08
文献标志码:
A
摘要:
以评教文本为研究对象,针对在评教文本中解释说明类反语的特点,该文构建包括主观矛盾、客观矛盾、情感程度的3种特征,提出了一种基于矛盾关系的评教文本解释说明类反语的检测算法.首先,将评教文本分为主观叙述文本与客观描述文本; 然后,使用语义分析的方法分析在主观叙述文本中的主观矛盾及在客观描述文本中的客观矛盾; 最后,对包含并列实体的文本进行情感程度分析,检测在评教文本中的解释说明类反语.该算法弥补了目前评教文本反语检测的缺失,对推动评教活动具有现实意义.
Abstract:
Taking the teaching evaluation text data as the research object,aiming at the characteristics of the explanatory irony in the teaching evaluation text data,three characteristics including subjective contradiction,objective contradiction and emotional degree are constructed and a set of irony detection algorithm based on contradiction relationship is proposed.Firstly,the text of teaching evaluation is divided into subjective narrative text and objective descriptive text.Then,the semantic analysis techniques is used to analyze the subjective contradiction of the subjective narrative text and the objective contradiction of the objective description text.Finally,the emotional degree of the text containing parallel entities is analyzed to detect the explanatory irony in the teaching evaluation text data.This algorithm makes up for the lack of irony detection in teaching evaluation texts,and has practical significance to promote teaching evaluation activities.

参考文献/References:

[1] 周荣翔,贾修一.中文反语识别特征分析 [J].山东大学学报(工学版),2019,49(1):41-46.
[2] KAROUI J,BENAMARA F,MORICEAU V.Towards a multilingual system for automatic irony detection [EB/OL].[2021-06-17].https://onlinelibrary.wiley.com/doi/10.1002/9781119671183.ch5.
[3] JI Tao,WU Yuanbin,LAN Man.Graph-based dependency parsing with graph neural networks [EB/OL].[2021-06-17].https://aclanthology.org/P19-1237/.
[4] DOZAT T,MANNING C D.Deep biaffine attention for neural dependency parsing [EB/OL].[2021-06-17].http://arxiv.org/pdf/1611.01734.
[5] ZHANG Yuan,ZHANG Yue.Tree communication models for sentiment analysis [EB/OL].[2021-06-17].https://aclanthology.org/P19-1342/.
[6] KULMIZEV A,LHONEUX M D,GONTRUM J,et al.Deep contextualized word embeddings in transition-based and graph-based dependency parsing a tale of two parsers revisited [EB/OL].[2021-06-17].https://arxiv.org/abs/1908.07397.
[7] ZHANG Zhisong,MA Xuezhe,HOVY E.An empirical investigation of structured output modeling for graph-based neural dependency parsing [EB/OL].[2021-06-17].https://aclanthology.org/P19-1562/.
[8] LHONEUX M D,BALLESTEROS M,NIVRE J.Recursive subtree composition in LSTM-based dependency parsing [EB/OL].[2021-06-17].https://arxiv.org/abs/1902.09781.
[9] FALENSKA A,KUHN J.The(non-)utility of structural features in BiLSTM-based dependency parsers [EB/OL].[2021-06-17].https://arxiv.org/abs/1905.12676.
[10] GÓMEZ-RODRÍGUEEZ C,VILARES D.Constituent parsing as sequence labeling [EB/OL].[2021-06-17].https://arxiv.org/pdf/1810.08994.pdf.
[11] VILARES D,ABDOU M.Better,faster,stronger sequence tagging constituent parsers [EB/OL].[2021-06-17].https://arxiv.org/abs/1902.10985.
[12] 滕少华,涂宏俊,刘冬宁.基于子结构逻辑的不确定性语义时态查询技术研究 [J].江西师范大学学报(自然科学版),2017,41(6):645-650.
[13] 罗春春.基于情感词典和机器人学习的微博情感极性分类策略研究 [D].太原:太原理工大学,2020.
[14] CAI Yi,YANG Kai,HUANG Dongping,et al.A hybrid model for opinion mining based on domain sentiment dictionary [EB/OL].[2021-06-17].https://doi.org/10.1007/s13042-017-0757-6.
[15] 徐雄飞,徐凡,王明文,等.中文微博句子倾向性分类中特征抽取研究 [J].江西师范大学学报(自然科学版),2015,39(3):290-296.
[16] 李文亮,杨秋翔,秦权.多特征混合模型文本情感分析方法 [J].计算机工程与应用,2021(19):1-12.
[17] 徐绪堪,周泽聿.基于多尺度BiLSTM-CNN的微信推文的情感分类模型及应用研究 [J].情报科学,2021,39(5):130-137.
[18] 蔡曙光,张笑,冯廷勇.“先扬后抑”vs.“先抑后扬”:反馈顺序对决策信心建构的影响 [J].心理科学,2016,39(3):686-692.
[19] 宋国民,张三强,贾奋励.基于GATE的中文时间信息抽取方法 [J].测绘工程,2021,30(1):1-5.
[20] 齐梅,胡敏.基于多方向空间词袋模型的物体识别 [J].计算机工程与应用,2017,53(7):197-201.
[21] 耿晓伟,姜宏艺.调节定向和调节匹配对情感预测中影响偏差的影响 [J].心理学报,2017,49(12):1537-1547.
[22] 易显飞,胡景谱.当代新兴“情感增强技术”的界定、类型与特征 [J].科学技术哲学研究,2019,36(3):70-75.
[23] 牛银菊,马崇武.索赔次数服从泊松负二项分布的风险模型的破产概率 [J].江西师范大学学报(自然科学版),2020,44(5):530-533.
[24] 方澄,李贝,韩萍.基于全局特征图的半监督微博文本情感分类 [J].信号处理,2021,37(6):1066-1074.

相似文献/References:

[1]唐宇坤,邓 松*,许梦雅,等.基于几何特征的学生评教数据离群点检测算法[J].江西师范大学学报(自然科学版),2021,(03):292.[doi:10.16357/j.cnki.issn1000-5862.2021.03.11]
　TANG Yukun,DENG Song*,XU Mengya,et al.The Outlier Detection Algorithm for Student Evaluation Data Based on Geometric Features[J].Journal of Jiangxi Normal University:Natural Science Edition,2021,(01):292.[doi:10.16357/j.cnki.issn1000-5862.2021.03.11]

备注/Memo

备注/Memo:
收稿日期:2021-09-12
基金项目:国家自然科学基金(61462037)资助项目.
通信作者:邓 松(1982—),男,江西南昌人,副教授,博士,主要从事实体关联、数据法学和教育信息化的研究.E-mail:47817086@qq.com
更新日期/Last Update: 2022-01-25