The ACM 4th International Conference on Information Technology for Social Good (GoodIT 2024) focuses on applying IT technologies to social good. Social good is typically defined as an action that benefits the public. In this case, Internet connection, education, and healthcare are all good examples of social goods. However, since new media innovations and the explosion of online communities have added new meaning to the term, social good is now about global citizens uniting to unlock the potential of individuals, technology, and collaboration to create positive societal impacts. This year, the conference took place in Bremen, from September 4th to September 6th. Two IML papers were accepted and presented at the conference.
Hannes Kath, Dr. Thiago S. Gouvêa and Prof. Dr.-Ing. Daniel Sonntag (from DFKI’s Interactive Machine Learning research department) received the Best PhD Colloquium Paper Award for their publication “Efficient Identification of Species in Multi-Label Bioacoustic Datasets” (1) (awarded among seven other contributions in the track).
The work explores various strategies for selecting new data points based on a combination of examined and unexamined data, aiming to maximize the likelihood of discovering recordings of previously unidentified species.
In the Work In Progress track, Aliki Anagnostopoulou presented ongoing research on modeling and evaluating explanations (2). This research extends an existing teacher-student dialogue dataset by adding annotations related to teaching strategies. Initial experiments using large language models (LLMs) demonstrate the complexity of the task. In addition, a test suite was developed based on effective teaching practices. The results were then compared against the five levels of teaching identified in the dataset.
(1) Hannes Kath, Thiago S. Gouvêa, and Daniel Sonntag. 2024. Active and Transfer Learning for Efficient Identification of Species in Multi-Label Bioacoustic Datasets. In Proceedings of the 2024 International Conference on Information Technology for Social Good (GoodIT ’24). Association for Computing Machinery, New York, NY, USA, 22–25. https://doi.org/10.1145/3677525.3678635
(2) Nils Feldhus, Aliki Anagnostopoulou, Qianli Wang, Milad Alshomary, Henning Wachsmuth, Daniel Sonntag, and Sebastian Möller. 2024. Towards Modeling and Evaluating Instructional Explanations in Teacher-Student Dialogues. In Proceedings of the 2024 International Conference on Information Technology for Social Good (GoodIT ’24). Association for Computing Machinery, New York, NY, USA, 225–230. https://doi.org/10.1145/3677525.3678665
