【论文速览】情感预测(Sentiment Prediction)
【文章1】Sentiment prediction using collaborative filtering
- 文章题目:Sentiment prediction using collaborative filtering
- 作者:Jihie Kim, Jaebong Yoo, Ho Lim, Huida Qiu, Zornitsa Kozareva, Aram Galstyan
- 关键词:sentiment prediction, collaborative filtering
- 时间:2013
- 来源:International AAAI Conference on Web and Social Media
- paper:https://www.aaai.org/ocs/index.php/ICWSM/ICWSM13/paper/view/6122 ,https://ojs.aaai.org/index.php/ICWSM/article/view/14461
- code:
- 引用:Kim, J., Yoo, J., Lim, H., Qiu, H., Kozareva, Z., & Galstyan, A. (2013). Sentiment Prediction Using Collaborative Filtering. Proceedings of the International AAAI Conference on Web and Social Media, 7(1).
abstract
Learning sentiment models from short texts such as tweets is a notoriously challenging problem due to very strong noise and data sparsity. This paper presents a novel, collaborative filtering-based approach for sentiment prediction in twitter conversation threads. Given a set of sentiment holders and sentiment targets, we assume we know the true sentiments for a small fraction of holder-target pairs. This information is then used to predict the sentiment of a previously unknown user towards another user or an entity using collaborative filtering algorithms. We validate our model on two Twitter datasets using different collaborative filtering tech- niques. Our preliminary results demonstrate that the proposed approach can be effectively used in twitter sentiment prediction, thus mitigating the data sparsity problem.
- 摘要:
由于强噪声和数据稀疏性,从推特等短文本中学习情感的模型是一类众所周知的具有挑战性的问题。本文提出了一种新的基于协作过滤的情感预测方法,应用于推特会话流之上。给定一组情感持有者和情感目标,我们假设我们知道一小部分持有者-目标组合的真实情绪。然后,利用协同过滤算法,将这些信息用于预测一个之前未知的用户对另一个用户或实体的情感。我们使用不同的协同过滤技术在两个Twitter数据集上验证了我们的模型。初步结果表明,该方法可以有效地用于推特情感预测,从而缓解数据稀疏问题。
感性认识
- 研究的基本问题
使用推特数据,利用协同过滤算法,进行一个用户对其他用户(或实体)的情感预测。
已知了一部分用户-用户(实体)间的情感关系,利用部分关系补全用户-用户(实体)情感关系矩阵。 - 现有问题
噪声强。用户的情感隐藏在字里行间,而不是特定的情感词汇。
数据稀疏。用户不会对所有话题,所有用户表达情感。 - 主要方法
数据:用户与用户之间的回复(讨论)数据流。一条回复表达着对上一句话的情感(支持/反对)。
模型主要想法:一个用户对特定目标(或另一个用户)的情感可以根据相似用户的情感来预测。
特征设计与表示方法:使用内容信息与回复关系来表示和预测情感。两种方式,分别是LIWC和深度网络(词嵌入)
协同过滤:以下几种策略,包括 1)用户平均值 2)基于相似用户的加权总和来预测 3)正则化SVD 4)PMF(概率矩阵分解), - 结果与结论
PMF在所有组合中表现最佳,深度学习产生了鲁棒的情感模型。总体趋势表明,RMSE随着密度的增加而减小。 - 不足与展望
实验研究和结果表明,协同过滤技术是一个有用的和强大的工具,可以生成用户的情绪档案。我们希望类似的方法可以用于其他会话数据,比如讨论政治问题的在线留言板。
因为retweet(转发)通常表示对消息的认可,我们计划将其整合到协同过滤框架中,并生成一个更强的模型。
【文章2】Tripartite graph clustering for dynamic sentiment analysis on social media
- 文章题目:Tripartite graph clustering for dynamic sentiment analysis on social media
- 作者:Zhu, Linhong;Galstyan, Aram;Cheng, James;Lerman, Kristina
- 关键词:
- 时间:2014
- 来源:Proceedings of the ACM SIGMOD International Conference on Management of Data
- paper:https://www.isi.edu/~linhong/Papers/SIGMOD14.pdf
- code:
- 引用:Zhu, L., A. Galstyan, James Cheng and Kristina Lerman. “Tripartite graph clustering for dynamic sentiment analysis on social media.” Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data (2014): n. pag.
abstract
The growing popularity of social media (e.g., Twitter) allows users
to easily share information with each other and influence others
by expressing their own sentiments on various subjects. In this
work, we propose an unsupervised tri-clustering framework, which
analyzes both user-level and tweet-level sentiments through co-
clustering of a tripartite graph. A compelling feature of the pro-
posed framework is that the quality of sentiment clustering of tweets,
users, and features can be mutually improved by joint clustering.
We further investigate the evolution of user-level sentiments and la-
tent feature vectors in an online framework and devise an efficient
online algorithm to sequentially update the clustering of tweets,
users and features with newly arrived data. The online framework
not only provides better quality of both dynamic user-level and
tweet-level sentiment analysis, but also improves the computational
and storage efficiency. We verified the effectiveness and efficiency
of the proposed approaches on the November 2012 California bal-
lot Twitter data.
待续……