Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909316618911744 |
|---|---|
| author | Faria, Fatema Tuj Johora Moin, Mukaffi Bin Rahman, Md. Mahfuzur Shanto, Md Morshed Alam Fahim, Asif Iftekher Hoque, Md. Moinul |
| author_facet | Faria, Fatema Tuj Johora Moin, Mukaffi Bin Rahman, Md. Mahfuzur Shanto, Md Morshed Alam Fahim, Asif Iftekher Hoque, Md. Moinul |
| contents | With the increasing popularity of daily information sharing and acquisition on the Internet, this paper introduces an innovative approach for intent classification in Bangla language, focusing on social media posts where individuals share their thoughts and opinions. The proposed method leverages multimodal data with particular emphasis on authorship identification, aiming to understand the underlying purpose behind textual content, especially in the context of varied user-generated posts on social media. Current methods often face challenges in low-resource languages like Bangla, particularly when author traits intricately link with intent, as observed in social media posts. To address this, we present the Multimodal-based Author Bangla Intent Classification (MABIC) framework, utilizing text and images to gain deeper insights into the conveyed intentions. We have created a dataset named "Uddessho," comprising 3,048 instances sourced from social media. Our methodology comprises two approaches for classifying textual intent and multimodal author intent, incorporating early fusion and late fusion techniques. In our experiments, the unimodal approach achieved an accuracy of 64.53% in interpreting Bangla textual intent. In contrast, our multimodal approach significantly outperformed traditional unimodal methods, achieving an accuracy of 76.19%. This represents an improvement of 11.66%. To our best knowledge, this is the first research work on multimodal-based author intent classification for low-resource Bangla language social media posts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09504 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language Faria, Fatema Tuj Johora Moin, Mukaffi Bin Rahman, Md. Mahfuzur Shanto, Md Morshed Alam Fahim, Asif Iftekher Hoque, Md. Moinul Computation and Language With the increasing popularity of daily information sharing and acquisition on the Internet, this paper introduces an innovative approach for intent classification in Bangla language, focusing on social media posts where individuals share their thoughts and opinions. The proposed method leverages multimodal data with particular emphasis on authorship identification, aiming to understand the underlying purpose behind textual content, especially in the context of varied user-generated posts on social media. Current methods often face challenges in low-resource languages like Bangla, particularly when author traits intricately link with intent, as observed in social media posts. To address this, we present the Multimodal-based Author Bangla Intent Classification (MABIC) framework, utilizing text and images to gain deeper insights into the conveyed intentions. We have created a dataset named "Uddessho," comprising 3,048 instances sourced from social media. Our methodology comprises two approaches for classifying textual intent and multimodal author intent, incorporating early fusion and late fusion techniques. In our experiments, the unimodal approach achieved an accuracy of 64.53% in interpreting Bangla textual intent. In contrast, our multimodal approach significantly outperformed traditional unimodal methods, achieving an accuracy of 76.19%. This represents an improvement of 11.66%. To our best knowledge, this is the first research work on multimodal-based author intent classification for low-resource Bangla language social media posts. |
| title | Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.09504 |