Exploring Semantic Relations for Social Media Sentiment Analysis

计算机科学 情绪分析 图像(数学) 名词 形容词 人工智能 情报检索 自然语言处理
作者
Jiandian Zeng,Jiantao Zhou,Caishi Huang
出处
期刊:IEEE/ACM transactions on audio, speech, and language processing [Institute of Electrical and Electronics Engineers]
卷期号:31: 2382-2394 被引量:8
标识
DOI:10.1109/taslp.2023.3285238
摘要

With the massive social media data available online, the conventional single modality emotion classification has developed into more complex models of multimodal sentiment analysis. Most existing works simply extracted image features at a coarse level, resulting in the absence of partially detailed visual features. Besides, social media data usually contain multiple images, while existing works considered a single image case and used only one image for representing visual features. In fact, it is nontrivial to extend the single image case to the multiple images case, due to the complex relations among multiple images. To solve the above issues, in this paper, we propose a G ated F usion S emantic R elation (GFSR) network to explore semantic relations for social media sentiment analysis. In addition to inter-relations between visual and textual modalities, we also exploit intra-relations among multiple images, potentially improving the sentiment analysis performance. Specifically, we design a gated fusion network to fuse global image embeddings and the corresponding local Adjective Noun Pair (ANP) embeddings. Then, apart from textual relations and cross-modal relations, we employ the multi-head cross attention mechanism between images and ANPs to capture similar semantic contents. Eventually, the updated textual and visual representations are concatenated for the final sentiment prediction. Extensive experiments are conducted on real-world Yelp and Flickr30k datasets, showing that our GFSR can improve about 0.10% to 3.66% in terms of accuracy on the Yelp dataset with multiple images, and achieve the best accuracy for two classes and the best macro F1 for three classes on the Flickr30k dataset with a single image.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
中大奖的英姑完成签到,获得积分10
1秒前
888发布了新的文献求助10
1秒前
cora发布了新的文献求助10
2秒前
旺仔完成签到 ,获得积分10
3秒前
小埋发布了新的文献求助10
3秒前
汉堡包应助xixi采纳,获得10
3秒前
眼睛大雨筠应助qq采纳,获得30
4秒前
5秒前
kaier完成签到 ,获得积分10
5秒前
望北楼主发布了新的文献求助10
6秒前
orangelion完成签到,获得积分10
6秒前
7秒前
7秒前
隐形曼青应助cora采纳,获得10
7秒前
7秒前
8秒前
9秒前
9秒前
10秒前
haibing发布了新的文献求助10
10秒前
李爱国应助断舍离采纳,获得10
10秒前
在水一方应助111采纳,获得10
11秒前
漾黎发布了新的文献求助10
12秒前
12秒前
是莉莉娅发布了新的文献求助30
12秒前
lily发布了新的文献求助30
12秒前
小芙爱雪碧完成签到 ,获得积分10
12秒前
14秒前
111发布了新的文献求助10
14秒前
深情安青应助Albertxkcj采纳,获得10
15秒前
微笑的白羊完成签到,获得积分20
16秒前
16秒前
17秒前
18秒前
传奇3应助邓柳采纳,获得10
18秒前
科研通AI5应助帅气男孩采纳,获得20
19秒前
19秒前
孙成成发布了新的文献求助10
19秒前
pbj发布了新的文献求助10
20秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969782
求助须知:如何正确求助?哪些是违规求助? 3514601
关于积分的说明 11174816
捐赠科研通 3249899
什么是DOI,文献DOI怎么找? 1795080
邀请新用户注册赠送积分活动 875599
科研通“疑难数据库(出版商)”最低求助积分说明 804886