Following the rise of e-commerce there has been a dramatic increase in online criminal activities targeting online shoppers. Considering that the number of online stores has risen dramatically, manually checking these stores has become intractable. An automated process is therefore required. We approached this problem by applying machine learning techniques to extract and detect instances of fraudulent online stores. Two sources of information were used to determine the legitimacy of an online store. First, contextual features extracted from the HTML and meta information were used to train various machine learning algorithms. Second, visual information, like the presence of social media logos, was added to make improvements on this baseline model. Results show a positive effect for adding visual information, increasing the F1-score from 0.93 to 0.98 over the baseline model. Finally, this research shows that visual information can improve recall during web crawling. CCS CONCEPTS• Information systems → Web mining; • Computing methodologies → Machine learning.

Word embeddings are used as building blocks for a wide range of natural language processing and information retrieval tasks. These embeddings are usually represented as continuous vectors, requiring significant memory capacity and computationally expensive similarity measures. In this study, we introduce a novel method for semantic hashing continuous vector representations into lowerdimensional Hamming space while explicitly preserving semantic information between words. This is achieved by introducing a Siamese autoencoder combined with a novel semantic preserving loss function. We show that our quantization model induces only a 4% loss of semantic information over continuous representations and outperforms the baseline models on several word similarity and sentence classification tasks. Finally, we show through cluster analysis that our method learns binary representations where individual bits hold interpretable semantic information. In conclusion, binary quantization of word embeddings significantly decreases time and space requirements while offering new possibilities through exploiting semantic information of individual bits in downstream information retrieval tasks.