Biblio

Emerging Machine Learning (ML) techniques, such as Deep Neural Network, are widely used in today's applications and services. However, with social awareness of privacy and personal data rapidly rising, it becomes a pressing and challenging societal issue to both keep personal data private and benefit from the data analytics power of ML techniques at the same time. In this paper, we argue that to avoid those costs, reduce latency in data processing, and minimise the raw data revealed to service providers, many future AI and ML services could be deployed on users' devices at the Internet edge rather than putting everything on the cloud. Moving ML-based data analytics from cloud to edge devices brings a series of challenges. We make three contributions in this paper. First, besides the widely discussed resource limitation on edge devices, we further identify two other challenges that are not yet recognised in existing literature: lack of suitable models for users, and difficulties in deploying services for users. Second, we present preliminary work of the first systematic solution, i.e. Zoo, to fully support the construction, composing, and deployment of ML models on edge and local devices. Third, in the deployment example, ML service are proved to be easy to compose and deploy with Zoo. Evaluation shows its superior performance compared with state-of-art deep learning platforms and Google ML services.

Online social networks (OSNs) have seen a remarkable rise in the presence of surreptitious automated accounts. Massive human user-base and business-supportive operating model of social networks (such as Twitter) facilitates the creation of automated agents. In this paper we outline a systematic methodology and train a classifier to categorise Twitter accounts into 'automated' and 'human' users. To improve classification accuracy we employ a set of novel steps. First, we divide the dataset into four popularity bands to compensate for differences in types of accounts. Second, we create a large ground truth dataset using human annotations and extract relevant features from raw tweets. To judge accuracy of the procedure we calculate agreement among human annotators as well as with a bot detection research tool. We then apply a Random Forests classifier that achieves an accuracy close to human agreement. Finally, as a concluding step we perform tests to measure the efficacy of our results.