Topic modelling on Instagram hashtags: An alternative way to Automatic Image Annotation?

• Published in: 2018 13th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP) pp. 61 - 67
• Main Authors: Argyrou, Argyris, Giannoulakis, Stamatios, Tsapatsoulis, Nicolas
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2018
• Subjects: Analytical models; automatic image annotation; Data models; Image annotation; Instagram hashtags; learning by example; Tagging; Topic modelling; Training; Twitter; Visualization
• DOI: 10.1109/SMAP.2018.8501887

Automatic Image Annotation (AIA) is the process of assigning tags to digital images without the intervention of humans. Most of the modern automatic image annotation methods are based on the learning by example paradigm. In those methods building the training examples, that is, pairs of images and related tags, is the first critical step. We have shown in our previous studies that hashtags accompanying images in social media and especially the Instagram provide a reach source for creating training sets for AIA. However, we concluded that only 20% of the Instagram hashtags describe the actual content of the image they accompany, thus, a series of filtering steps need to apply in order to identify the appropriate hashtags. In this paper we apply topic modelling with Latent Dirichlet Allocation (LDA) on Instagram hashtags in order to predict the subject of the related images. Since a topic is composed by a set of related terms, the identification of the visual topic of an Instagram image, through the proposed method, provides a plausible set of tags to be used in the context of training AIA methods.