Abstract--Recent years have witnessed an explosive growth of mobile devices. Mobile devices are permeating every aspect of our daily lives. With the increasing usage of mobile devices and intelligent applications, there is a soaring demand for mobile applications with machine learning services. Inspired by the tremendous success achieved by deep learning in many machine learning tasks, it becomes a natural trend to push deep learning towards mobile applications. However, there exist many challenges to realize deep learning in mobile applications, including the contradiction between the miniature nature of mobile devices and the resource requirement of deep neural networks, the privacy and security concerns about individuals' data, and so on. To resolve these challenges, during the past few years, great leaps have been made in this area. In this paper, we provide an overview of the current challenges and representative achievements about pushing deep learning on mobile devices from three aspects: training with mobile data, efficient inference on mobile devices, and applications of mobile deep learning. The former two aspects cover the primary tasks of deep learning. Then, we go through our two recent applications that apply the data collected by mobile devices to inferring mood disturbance and user identification. Finally, we conclude this paper with the discussion of the future of this area. The past few years have witnessed an explosive growth of mobile devices which is expected to continue in the next decades. It is predicted that mobile devices will reach 5.6 billion, accounting for 21% of all networked devices in 2020 [1].

We present a neural framework for opinion summarization from online product reviews which is knowledge-lean and only requires light supervision (e.g., in the form of product domain labels and user-provided ratings). Our method combines two weakly supervised components to identify salient opinions and form extractive summaries from multiple reviews: an aspect extractor trained under a multi-task objective, and a sentiment predictor based on multiple instance learning. We introduce an opinion summarization dataset that includes a training set of product reviews from six diverse domains and human-annotated development and test sets with gold standard aspect annotations, salience labels, and opinion summaries. Automatic evaluation shows significant improvements over baselines, and a large-scale study indicates that our opinion summaries are preferred by human judges according to multiple criteria.

Although there are millions of transgender people in the world, a lack of information exists about their health issues. This issue has consequences for the medical field, which only has a nascent understanding of how to identify and meet this population's health-related needs. Social media sites like Twitter provide new opportunities for transgender people to overcome these barriers by sharing their personal health experiences. Our research employs a computational framework to collect tweets from self-identified transgender users, detect those that are health-related, and identify their information needs. This framework is significant because it provides a macro-scale perspective on an issue that lacks investigation at national or demographic levels. Our findings identified 54 distinct health-related topics that we grouped into 7 broader categories. Further, we found both linguistic and topical differences in the health-related information shared by transgender men (TM) as com-pared to transgender women (TW). These findings can help inform medical and policy-based strategies for health interventions within transgender communities. Also, our proposed approach can inform the development of computational strategies to identify the health-related information needs of other marginalized populations.

The ever-growing datasets published on Linked Open Data mainly contain encyclopedic information. However, there is a lack of quality structured and semantically annotated datasets extracted from unstructured real-time sources. In this paper, we present principles for developing a knowledge graph of interlinked events using the case study of news headlines published on Twitter which is a real-time and eventful source of fresh information. We represent the essential pipeline containing the required tasks ranging from choosing background data model, event annotation (i.e., event recognition and classification), entity annotation and eventually interlinking events. The state-of-the-art is limited to domain-specific scenarios for recognizing and classifying events, whereas this paper plays the role of a domain-agnostic road-map for developing a knowledge graph of interlinked events.

ABSTRACT The availability of powerful Natural Language Processing techniques led to the emergence of AI tool that reads and interprets unstructured textual information, such as news and social media messages. The sentiment of finance-related content influences trading and investment decisions of players in financial markets and hence, moves the prices of assets. Dr. Svetlana Borovkova has been working for several years in the area of sentiment analysis and its relation to financial markets; applications of sentiment analysis range from commodity trading to systemic risk to quantitative investment strategies. In this talk, Dr. Borovkova will give an overview of this exciting field and show, among other things, how media sentiment can be used to forecast global financial distress, to generate sector and country rotation investment strategies and to help enhance machine learning applications to intraday trading. SPEAKER Dr. Svetlana Borovkova is an Associate Professor of Quantitative Finance in Vrije Universiteit Amsterdam and Head of Quantitative Modelling in risk advisory firm Probability & Partners.

The growing importance of digital demand generation channels in the B2B marketing mix was reflected by the results of DemandGen's 2018 Benchmark Survey Report. Out of the ten channels most effective in driving "early-stage engagement" and "driving conversions later in the funnel," eight were digital. These findings aren't astonishing to anyone engaged in B2B marketing. While analog channels, like in-person events, are still effective ways to drive demand, the shift to digital has been underway for more than a decade. As technology continues to be developed and embraced at increasing speeds, demand marketers are rushing to keep up.

While a decade ago China was known to be the "world's factory," manufacturing everyday household goods for companies across the globe, in recent years tech and internet companies have redefined the face of Chinese industry. Both Tencent and Alibaba are now among the world's top 10 most valuable companies. Indeed, Chinese companies are now leading the way in the most disruptive global tech trends, including autonomous vehicles, machine learning and blockchain. According to Deloitte, global CFOs' optimism about the Chinese market has never been higher. But all this innovation has come with a side effect: Chinese consumers' expectations of brands and businesses have risen to match the market's optimism.

This paper discusses technology challenges and opportunities to embrace artificial intelligence (AI) era in the design of wireless networks. We aim to provide readers with motivation and general methodology for adoption of AI in the context of next-generation networks. First, we discuss the rise of network intelligence and then, we introduce a brief overview of AI with machine learning (ML) and their relationship to self-organization designs. Finally, we discuss design of intelligent agent and it's functions to enable knowledge-driven wireless networks with AI.

This survey presents the main results achieved for the influence maximization problem in social networks. This problem is well studied in the literature and, thanks to its recent applications, some of which currently deployed on the field, it is receiving more and more attention in the scientific community. The problem can be formulated as follows: given a graph, with each node having a certain probability of influencing its neighbors, select a subset of vertices so that the number of nodes in the network that are influenced is maximized. Starting from this model, we introduce the main theoretical developments and computational results that have been achieved, taking into account different diffusion models describing how the information spreads throughout the network, various ways in which the sources of information could be placed, and how to tackle the problem in the presence of uncertainties affecting the network. Finally, we present one of the main application that has been developed and deployed exploiting tools and techniques previously discussed.

DBSCAN may not be sufficient when the input data type is heterogeneous in terms of textual description. When we aim to discover clusters of geo-tagged records relevant to a particular point-of-interest (POI) on social media, examining only one type of input data (e.g., the tweets relevant to a POI) may draw an incomplete picture of clusters due to noisy regions. To overcome this problem, we introduce DBSTexC, a newly defined density-based clustering algorithm using spatio--textual information. We first characterize POI-relevant and POI-irrelevant tweets as the texts that include and do not include a POI name or its semantically coherent variations, respectively. By leveraging the proportion of POI-relevant and POI-irrelevant tweets, the proposed algorithm demonstrates much higher clustering performance than the DBSCAN case in terms of $\mathcal{F}_1$ score and its variants. While DBSTexC performs exactly as DBSCAN with the textually homogeneous inputs, it far outperforms DBSCAN with the textually heterogeneous inputs. Furthermore, to further improve the clustering quality by fully capturing the geographic distribution of tweets, we present fuzzy DBSTexC (F-DBSTexC), an extension of DBSTexC, which incorporates the notion of fuzzy clustering into the DBSTexC. We then demonstrate the robustness of F-DBSTexC via intensive experiments. The computational complexity of our algorithms is also analytically and numerically shown.