Papers by Sooji Han
RP-DNN: A Tweet Level Propagation Context Based Deep Neural Networks for Early Rumor Detection in Social Media (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for early rumor detection on social media platforms are limited, incomplete and noisy. |
| Approach: | They propose a novel hybrid neural network architecture which combines a task-specific character-based bidirectional language model and stacked Long Short-Term Memory (LSTM) networks to represent textual contents and social-temporal contexts of input source tweets. |
| Outcome: | The proposed model achieves state-of-the-art for detecting unseen rumors on large augmented data which covers more than 12 events and 2,967 rumors. |
Hierarchical Attention Network for Explainable Depression Detection on Twitter Aided by Metaphor Concept Mappings (2022.coling-1)
Copied to clipboard
| Challenge: | Existing black-box-like deep learning methods for depression detection focus on improving classification performance, but it is impossible to explain and interpret those models that rely on state-of-the-art (SOTA) deep learning techniques. |
| Approach: | They propose to use hierarchical attention mechanisms and feed-forward neural networks to encode a model for depression detection on Twitter that leverages metaphorical concept mappings as input. |
| Outcome: | The proposed model leverages metaphorical concept mappings as input to detect depressed individuals and identify features of such users’ tweets. |
Effective Crowdsourcing of Multiple Tasks for Comprehensive Knowledge Extraction (2020.lrec-1)
Copied to clipboard
Sangha Nam, Minho Lee, Donghwan Kim, Kijong Han, Kuntae Kim, Sooji Yoon, Eun-kyung Kim, Key-Sun Choi
| Challenge: | Existing studies on information extraction from unstructured texts lack a coherent evaluation of all tasks. |
| Approach: | They propose to use crowdsourcing data to develop a Korean information extraction initiative point . they propose to train and evaluate four Korean information extracting tasks using a state-of-the-art model . |
| Outcome: | The proposed model will be used to evaluate four Korean information extraction tasks using crowdsourcing data. |