Crowdfunding has seen an enormous rise, becoming a new alternative funding source for emerging companies or new startups in recent years. As crowdfunding prevails, it is also under substantial risk of the occurrence of fraud. Though a growing number of articles indicate that crowdfunding scams are a new imminent threat to investors, little is known about them primarily due to the lack of measurement data collected from real scam cases. This paper fills the gap by collecting, labeling, and analyzing publicly available data of a hundred fraudulent campaigns on a crowdfunding platform. In order to find and understand distinguishing characteristics of crowdfunding scams, we propose to use a broad range of traits including project-based traits, project creator-based ones, and content-based ones such as linguistic cues and Named Entity Recognition features, etc. We then propose to use the feature selection method called Forward Stepwise Logistic Regression, through which 17 key discriminating features (including six original and hitherto unused ones) of scam campaigns are discovered. Based on the selected 17 key features, we present and discuss our findings and insights on distinguishing characteristics of crowdfunding scams, and build our scam detection model with 87.3% accuracy. We also explore the feasibility of early scam detection, building a model with 70.2% of classification accuracy right at the time of project launch. We discuss what features from which sections are more helpful for early scam detection on day 0 and thereafter.

In recent years, crowdfunding has emerged as an alternative funding source for startups and emerging businesses, experiencing significant growth. However, this growth has also led to an increase in fraudulent activities. Despite the potential for fraud in the realm of crowdfunding, there is limited knowledge of the phenomenon due to a lack of data on actual instances of fraudulent campaigns. In this paper, we aim to address this deficiency by collecting and analyzing publicly accessible web and social media data from a hundred fraudulent crowdfunding projects. In order to identify and comprehend the distinguishing characteristics of fraudulent campaigns, we first propose (i) using a wide variety of characteristics of campaign projects and project creators, including their profiles, behavior, social traits, and language. Then, (ii) we propose to use and combine three well-known multiple feature selection methods, which are based on Correlation-based Feature Selection (CFS), Pearson Correlation Coefficient (PCC), and Information Gain (IG), to identify representative features of fraudulent campaigns. Our approach identifies 10 commonly selected key features of fraudulent crowdfunding campaigns, three of which are new, original findings. We provide and discuss our findings and interpretations on the 10 commonly selected key features in relation to previous studies, based on which we construct a fraud detection model with 82.04% accuracy. We also employ Shapley Additive ExPlanations (SHAP) to interpret the fraud detection model, explaining the importance of each feature.

As Deep Learning (DL) algorithms have rapidly become a methodology of choice in various domains, they have recently entered also the field of the Internet traffic classification, successfully demonstrating impressive results. Most of the research work up to this point has focused on improving the accuracy of classification systems, yet there has been little attempt to provide (i) systematic comparison of the various DL algorithms used and (ii) analysis on where the higher accuracy come from, particularly when comparing with the traditional machine learning algorithms like C4.5. To fill this gap, we conduct experiments with four DL algorithms proposed for traffic classification, including CNN, LSTM, Stacked Auto-Encoder (SAE), and Hierarchical Attention Networks (HAN). Further, we propose to leverage and visualize hierarchical attention layers to highlight which parts of the traffic packet traces were most informative for accurate classification, which provides hints about why (and how) DL algorithms achieve the state-of-the-art level high accuracy. We view this paper as the first step towards answering the aforementioned "why" question, which is critical in understanding the real benefit and contribution of deep learning to the field of the Internet traffic classification, and advancing its state-of-the-art.

Smart SNS Map: Location-based Social Network Service Data Mapping and Visualization System Sentiment Analysis;Word Cloud;Data;Twitter;Instagram;Online Social Networks;GPS;Mapping; Hundreds of millions of new posts and information are being uploaded and propagated everyday on Online Social Networks(OSN) like Twitter, Facebook, or Instagram. This paper proposes and implements a GPS-location based SNS data mapping, analysis, and visualization system, called Smart SNS Map, which collects SNS data from Twitter and Instagram using hundreds of PlanetLab nodes distributed across the globe. Like no other previous systems, our system uniquely supports a variety of functions, including GPS-location based mapping of collected tweets and Instagram photos, keyword-based tweet or photo searching, real-time heat-map visualization of tweets and instagram photos, sentiment analysis, word cloud visualization, etc. Overall, a system like this, admittedly still in a prototype phase though, is expected to serve a role as a sort of social weather station sooner or later, which will help people understand what are happening around the SNS users, systems, society, and how they feel about them, as well as how they change over time and/or space.

Crowdfunding has emerged as an alternative funding source among entrepreneurs, businesses, and industries. In recent years, research on machine learning-based project classification models has been conducted with the aim of predicting the success of crowdfunding campaigns, both for entrepreneurs and investors. However, most of the research has focused on classification approaches using non-content information such as project metadata, creators’ behavior, and social history, but there have been few attempts to use text content data per se, particularly in order to provide explanations and evidence for how the prediction decisions were made. To address this point, we propose to use a deep learning-based approach called Hierarchical Attention Network (HAN) to predict the success of crowdfunding campaigns and provide explanation and justification of the prediction decisions using attention weights. We collect publicly available data of crowdfunding campaigns and build our success prediction model with an accuracy of 86.38% and 87.29%, using an Updates section and backers’ comments in a Comments section, respectively. We also explore the feasibility of early success prediction during the funding period (up to 2 months), with as much as 80.99% accuracy in 1 to 2 months. Finally, we examine word and sentence attention weight scores to clarify key factors in predicting crowdfunding success.