基于pu-learning的同行评议文本情感分析  

Sentiment Analysis of Peer Review Texts Based on Pu-Learning

作　　者：林原[1] 王凯巧 杨亮[3] 林鸿飞[3] 任璐 丁堃[1] LIN Yuan;WANG Kaiqiao;YANG Liang;LIN Hongfei;REN Lu;DING Kun(Institute of Science of Science and Science&Technology,Dalian University of Technology,Dalian,Liaoning 116024,China;Haikou Laboratory,Institute of Acoustic,Chinese Academy of Sciences,Haikou 570105,China;Information Retrieval Laboratory,Dalian University of Technology,Dalian,Liaoning 116023,China)

机构地区：[1]大连理工大学科学学与科技管理研究所,辽宁大连116024 [2]中国科学院声学研究所南海研究站,海口570105 [3]大连理工大学信息检索实验室,辽宁大连116023

出　　处：《计算机工程与应用》2023年第3期143-149,共7页Computer Engineering and Applications

基　　金：国家自然科学基金面上项目(61976036,61772103);大连理工大学研究生教改基金(JG_2021040)。

摘　　要：最近几年逐渐出现了对同行评议文本情感分析的研究,包括通过同行评议文本预测审稿人的推荐状态的任务。现有模型融入了论文本身或摘要信息,采用神经网络学习论文或摘要的高层表示,结合同行评议文本预测审稿人的推荐状态,这使得模型变得非常复杂的同时结果却没有实质性的提高。为此,提出了OSA机制来提高情感分析模型中对观点句的关注度。具体来说,采用pu-learning从同行评议文本的前N个句子中学习观点句的特征,使每一个句子都得到一个观点句权重,将其应用于情感分析模型的倒数第二层,由此得到最终的预测结果。在ICLR2017—2018数据集上使用不同的情感分析模型对OSA进行了评估,实验结果验证了OSA的高效性,并在两个数据集上取得了优异的性能。There have been some researches on the sentiment analysis of peer review text, including the task of predicting the overall recommendation through a peer review text written by reviewer for a submission. Existing works integrate the embedding of the paper or abstract, utilizing neural network to learn the high-level representation of paper or abstract and review text to predict reviewer’s overall recommendation which make the algorithm very complicated but the effect is not substantially improved. To solve this issue, a mechanism called OSA(opinionated sentence attention)is proposed to make opinionated sentences get more attention in sentiment analysis model. Specifically, this paper employs a positive-unlabeled learning method to learn opinionated sentence features form Top-N sentences of peer review texts so that every sentence of all review texts get a opinionated weight, then these weights are dotted with penultimate layer of neural network to get the final prediction. OSA is evaluated with different neural networks on ICLR 2017—2018 datasets,experimental results verify that OSA is high efficiency and achieves outstanding performance on two datasets.

关 键 词：同行评议 情感分析 pu-learning 数据挖掘 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]