Few-shot Learning for Multi-modal Social Media Event Filtering

被引:3
|
作者
Nascimento, Jose [1 ]
Cardenuto, Joao Phillipe [1 ]
Yang, Jing [1 ]
Rocha, Anderson [1 ]
机构
[1] Univ Estadual Campinas, Inst Comp, Artificial Intelligence Lab Recod Ai, Campinas, SP, Brazil
基金
瑞典研究理事会; 巴西圣保罗研究基金会;
关键词
event filtering; few-shot learning; social media dataset;
D O I
10.1109/WIFS55849.2022.9975429
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Social media has become an important data source for event analysis. When collecting this type of data, most contain no useful information to a target event. Thus, it is essential to filter out those noisy data at the earliest opportunity for a human expert to perform further inspection. Most existing solutions for event filtering rely on fully supervised methods for training. However, in many real-world scenarios, having access to large number of labeled samples is not possible. To deal with a few labeled sample training problem for event filtering, we propose a graph-based few-shot learning pipeline. We also release the Brazilian Protest Dataset to test our method. To the best of our knowledge, this dataset is the first of its kind in event filtering that focuses on protests in multi-modal social media data, with most of the text in Portuguese. Our experimental results show that our proposed pipeline has comparable performance with only a few labeled samples (60) compared with a fully labeled dataset (3100). To facilitate the research community, we make our dataset and code available at https://github.com/jdnascim/7Set-AL.
引用
收藏
页数:6
相关论文
共 50 条
  • [21] TMD-FS: Improving Few-Shot Object Detection with Transformer Multi-modal Directing
    Yuan, Ying
    Duan, Lijuan
    Wang, Wenjian
    En, Qing
    PATTERN RECOGNITION AND COMPUTER VISION, PT IV, 2021, 13022 : 447 - 458
  • [22] Active Few-Shot Learning for Sound Event Detection
    Wang, Yu
    Cartwright, Mark
    Bello, Juan Pablo
    INTERSPEECH 2022, 2022, : 1551 - 1555
  • [23] Extensively Matching for Few-shot Learning Event Detection
    Viet Dac Lai
    Dernoncourt, Franck
    Thien Huu Nguyen
    NARRATIVE UNDERSTANDING, STORYLINES, AND EVENTS, 2020, : 38 - 45
  • [24] Meta-Style: Few-Shot Learning Dataset for Social Media Field
    Peng, Yuncong
    Fu, Boyi
    Qin, Xiaolin
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT IV, 2022, 13532 : 433 - 444
  • [25] Few-Shot Few-Shot Learning and the role of Spatial Attention
    Lifchitz, Yann
    Avrithis, Yannis
    Picard, Sylvaine
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 2693 - 2700
  • [26] Lite-MKD: A Multi-modal Knowledge Distillation Framework for Lightweight Few-shot Action Recognition
    Liu, Baolong
    Zheng, Tianyi
    Zheng, Peng
    Liu, Daizong
    Qu, Xiaoye
    Gao, Junyu
    Dong, Jianfeng
    Wang, Xun
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 7283 - 7294
  • [27] MsPrompt: Multi-step prompt learning for debiasing few-shot event detection
    Wang, Siyuan
    Zheng, Jianming
    Cai, Fei
    Song, Chengyu
    Luo, Xueshan
    INFORMATION PROCESSING & MANAGEMENT, 2023, 60 (06)
  • [28] Graph Learning Regularization and Transfer Learning for Few-Shot Event Detection
    Viet Dac Lai
    Minh Van Nguyen
    Thien Huu Nguyen
    Dernoncourt, Franck
    SIGIR '21 - PROCEEDINGS OF THE 44TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2021, : 2172 - 2176
  • [29] Multi-view distillation based on multi-modal fusion for few-shot action recognition (CLIP-MDMF)
    Guo, Fei
    Wang, Yikang
    Qi, Han
    Jin, Wenping
    Zhu, Li
    Sun, Jing
    KNOWLEDGE-BASED SYSTEMS, 2024, 304
  • [30] FEW-SHOT ACOUSTIC EVENT DETECTION VIA META LEARNING
    Shi, Bowen
    Sun, Ming
    Puvvada, Krishna C.
    Kao, Chieh-Chi
    Matsoukas, Spyros
    Wang, Chao
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 76 - 80