About Emotion Identification in Visual Sentiment Analysis

Proceedings of Recent Advances in Natural Language Processing, pages 258–265, Hissar, Bulgaria, Sep 7–9 2015. About Emotion Identification in Visual Sentiment Analysis Olga Kanishcheva Institute of Information and Communication Technologies, Bulgarian Academy of Sciences kanichshevaolga@gmail.com Galia Angelova Institute of Information and Communication Technologies, Bulgarian Academy of Sciences galia@lml.bas.bg Abstract In this paper we present an approach for anal- ysis of sentiments and emotions in image tag- ging using SentiWordNet as an external lin- guistic resource of emotional words. Our aim is to design and implement algorithms that as- sess the emotions and polarity given a set of image tags. The approach is not limited to ob- ject analysis only (considering informational keywords) but deals with the involvement tags and employs some techniques used for senti- ment analysis in social networks. We consider the issue of tag sense disambiguation when image keywords are mapped to SentiWordNet. The Lesk algorithm helps to identify correctly the meaning of about 50% of the ambiguous single keywords of 200 images. The total number of tags we process is about 10,000. Calculating a "sentiment score" for each im- age, the system classifies images into three classes (positive, negative, neutral). These classes are compared to emotional assessments done (i) by humans and (ii) by training of a SVM classifier that provides the baseline of 69.7% precision, 29.9% recall and 41.8% F- measure. Our approach works with 63.53% precision, 58.7% recall and 61.02% F- measure. The experiments are performed using the annotations of the industrial auto-tagging platform Imagga that identifies automatically image objects with high precision. 1 Introduction Folksonomies are recognized as a recent type of internet classification system where non- professional users add their own keywords (tags) to information objects. These tags could then be used by anyone to sort and share items. "Folk- sonomy" became the word most commonly used to refer to this annotation approach that is also known as ethnoclassification, social classifica- tion/tagging, collaborative tagging, social index- ing and distributed classification. Peters and Weller (2008) wrote that annotation development via crowdsourcing and the resulting folksonomies provide many advantages such as diverse opinions, independent decision-making, decentralization of power, and a way of aggre- gating opinions. Most current systems that facili- tate tagging do not require any sort of text verifi- cation or controlled vocabulary. In this way the diversity of opinions allowed in tagging is limit- less and the annotators independently select the tags they want to use. Finally, folksonomies pro- vide the aggregation of opinions in the form of systems such as Flickr (https://www.flickr.com), Instagram (https://instagram.com/), Picasaweb (picasaweb.com/), Photobucket (http://photo bucket.com/) and others. Images in these large collections are retrieved using keywords specified by users. For example, searching with tag "London" returns the list of links to all photos annotated with this keyword. Thus the semantic information, which is saved up in the metadata, enables the development of various searching strategies that rely significant- ly on automatic text processing, lexical hierar- chies and information search techniques. Emotional words take special place among folksonomy tags. …

Content truncated to 500 words