Multimodal Classification of Sexist Advertisements

Advertisements, especially in online social media, are often based on visual and/or textual persuasive messages, frequently showing women as subjects. Some of these advertisements create a biased portrays of women, finally resulting as sexist and in some cases misogynist. In this paper we give a first insight in the field of automatic detection of sexist multimedia contents, by proposing both a unimodal and a multimodal approach. In the unimodal approach we propose binary classifiers based on different visual features to automatically detect sexist visual content. In the multimodal approach both visual and textual features are considered. We created a manually labeled database of sexist and non sexist advertisements, composed of two main datasets: a first one containing 423 advertisements with images that have been considered sexist (or non sexist) with respect to their visual content, and a second dataset comprising 192 advertisements labeled as sexist and non sexist according to visual and/or textual cues. We adopted the first dataset to train a visual classifier. Finally we proved that a multimodal approach that considers the trained visual classifier and a textual one permits good classification performance on the second dataset, reaching 87% of recall and 75% of accuracy, which are significantly higher than the performance obtained by each of the corresponding unimodal approaches.

[1]  Q. M. Jonathan Wu,et al.  3D Shape from Focus and Depth Map Computation Using Steerable Filters , 2009, ICIAR.

[2]  Bailey Poland,et al.  Haters: Harassment, Abuse, and Violence Online , 2016 .

[3]  Raimondo Schettini,et al.  Recall or precision-oriented strategies for binary classification of skin pixels , 2008, J. Electronic Imaging.

[4]  C. Koch,et al.  Computational modelling of visual attention , 2001, Nature Reviews Neuroscience.

[5]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[6]  Rainer Lienhart,et al.  A survey on visual adult image recognition , 2012, Multimedia Tools and Applications.

[7]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[8]  Raimondo Schettini,et al.  Contrast image correction method , 2010, J. Electronic Imaging.

[9]  Dong Liu,et al.  Towards a comprehensive computational model foraesthetic assessment of videos , 2013, MM '13.

[10]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[11]  Zhouyu Fu,et al.  Recognition of Pornographic Web Pages by Classifying Texts and Images , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Paolo Rosso,et al.  Automatic Identification and Classification of Misogynistic Language on Twitter , 2018, NLDB.

[13]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[14]  Urbano Nunes,et al.  Trainable classifier-fusion schemes: An application to pedestrian detection , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[15]  Emmanuella Plakoyiannaki,et al.  Images of Women in Online Advertisements of Global Products: Does Sexism Exist? , 2008 .

[16]  Thanassis Tiropanis,et al.  The problem of identifying misogynist language on Twitter (and other online social spaces) , 2016, WebSci.

[17]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Sabine Süsstrunk,et al.  Measuring colorfulness in natural images , 2003, IS&T/SPIE Electronic Imaging.

[19]  Gianluigi Ciocca,et al.  Genetic programming approach to evaluate complexity of texture images , 2016, J. Electronic Imaging.

[20]  Hideyuki Tamura,et al.  Textural Features Corresponding to Visual Perception , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[21]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[22]  B. B. Zaidan,et al.  An Automated Anti-Pornography System using a Skin Detector Based on Artificial Intelligence: a Review , 2013, Int. J. Pattern Recognit. Artif. Intell..

[23]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[24]  J. Dahlberg,et al.  The Sexual Objectification of Women in Advertising : A Contemporary Cuiturai Perspective , 2008 .

[25]  Yuanzhen Li,et al.  Measuring visual clutter. , 2007, Journal of vision.

[26]  Silvia Corchs,et al.  Ensemble learning on visual and textual data for social image emotion classification , 2017, International Journal of Machine Learning and Cybernetics.

[27]  Gianluigi Ciocca,et al.  Predicting Complexity Perception of Real World Images , 2016, PloS one.