Please use this identifier to cite or link to this item:
|Title:||Topic modelling on Instagram hashtags: an alternative way to Automatic Image Annotation?||Authors:||Argyrou, Argyris
|Keywords:||Automatic image annotation;Instagram hashtags;Learning by example;Topic modelling||Category:||Computer and Information Sciences||Field:||Natural Sciences||Issue Date:||Sep-2018||Publisher:||Institute of Electrical and Electronics Engineers Inc.||Source:||13th International Workshop on Semantic and Social Media Adaptation and Personalization, 2018, 6-7 September, Zaragoza, Spain||Conference:||13th International Workshop on Semantic and Social Media Adaptation and Personalization, SMAP 2018||Abstract:||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.||URI:||http://ktisis.cut.ac.cy/handle/10488/13427||DOI:||10.1109/SMAP.2018.8501887||Rights:||© 2018 IEEE.||Type:||Conference Papers|
|Appears in Collections:||Δημοσιεύσεις σε συνέδρια/Conference papers|
Show full item record
checked on Nov 18, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.