We can often detect from a person’s utterances whether he or she is in favor of or against a given target entity—one’s stance toward the target. However, a person may express the same stance toward a target by using negative or positive language. Here for the first time we present a dataset of tweet–target pairs annotated for both stance and sentiment. The targets may or may not be referred to in the tweets, and they may or may not be the target of opinion in the tweets. Partitions of this dataset were used as training and test sets in a SemEval-2016 shared task competition. We propose a simple stance detection system that outperforms submissions from all 19 teams that participated in the shared task. Additionally, access to both stance and sentiment annotations allows us to explore several research questions. We show that although knowing the sentiment expressed by a tweet is beneficial for stance classification, it alone is not sufficient. Finally, we use additional unlabeled data through distant supervision techniques and word embeddings to further improve stance classification.

Stance and Sentiment in Tweets

We can often detect from a person's utterances whether he/she is in favor of or against a given target entity -- their stance towards the target. However, a person may express the same stance towards a target by using negative or positive language. Here for the first time we present a dataset of tweet--target pairs annotated for both stance and sentiment. The targets may or may not be referred to in the tweets, and they may or may not be the target of opinion in the tweets. Partitions of this dataset were used as training and test sets in a SemEval-2016 shared task competition. We propose a simple stance detection system that outperforms submissions from all 19 teams that participated in the shared task. Additionally, access to both stance and sentiment annotations allows us to explore several research questions. We show that while knowing the sentiment expressed by a tweet is beneficial for stance classification, it alone is not sufficient. Finally, we use additional unlabeled data through distant supervision techniques and word embeddings to further improve stance classification.

We study the problem of predicting the Field-of-Views (FoVs) of viewers watching 360° videos using commodity Head-Mounted Displays (HMDs). Existing solutions either use the viewer's current orientation to approximate the FoVs in the future, or extrapolate future FoVs using the historical orientations and dead-reckoning algorithms. In this paper, we develop fixation prediction networks that concurrently leverage sensor- and content-related features to predict the viewer fixation in the future, which is quite different from the solutions in the literature. The sensor-related features include HMD orientations, while the content-related features include image saliency maps and motion maps. We build a 360° video streaming testbed to HMDs, and recruit twenty-five viewers to watch ten 360° videos. We then train and validate two design alternatives of our proposed networks, which allows us to identify the better-performing design with the optimal parameter settings. Trace-driven simulation results show the merits of our proposed fixation prediction networks compared to the existing solutions, including: (i) lower consumed bandwidth, (ii) shorter initial buffering time, and (iii) short running time.

Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality

Nowadays, with the development of cyber-physical systems (CPS), there are an increasing amount of applications deployed in the CPS to connect cyber space with physical world better and closer than ever. Furthermore, the cloud-based CPS bring massive computing and storage resource for CPS, which enables a wide range of applications. Meanwhile, due to the explosive expansion of applications deployed on the CPS, the energy consumption of the cloud-based CPS has received wide concern. To improve the energy efficiency in the cloud environment, the virtualized technology is employed to manage the resources, and the applications are generally hosted by virtual machines (VMs). However, it remains challenging to meet the Quality-of-Service (QoS) requirements. In view of this challenge, a QoS-aware VM scheduling method for energy conservation, named QVMS, in cloud-based CPS is designed. Technically, our scheduling problem is formalized as a standard multi-objective problem first. Then, the Non-dominated Sorting Genetic Algorithm III (NSGA-III) is adopted to search the optimal VM migration solutions. Besides, SAW (Simple Additive Weighting) and MCDM (Multiple Criteria Decision Making) are employed to select the most optimal scheduling strategy. Finally, simulations and experiments are conducted to verify the effectiveness of our proposed method.

A QoS-aware virtual machine scheduling method for energy conservation in cloud-based cyber-physical systems

Virtual reality (VR) over wireless is emerging as an important use case of 5G networks. Fully-immersive VR experience requires the wireless delivery of huge data at ultra-low latency, thus leading to ultra-high transmission rate requirement for wireless communications. This challenge can be largely addressed by the recent network architecture known as mobile edge computing (MEC) network, which enables caching and computing capabilities at the edge of wireless networks. This paper presents a novel MEC-based mobile VR delivery framework that is able to cache parts of the field of views (FOVs) in advance and compute certain post-processing procedures on demand at the mobile VR device. To minimize the average required transmission rate, we formulate the joint caching and computing optimization problem to determine which FOVs to cache, whether to cache them in 2D or 3D as well as which FOVs to compute at the mobile device under cache size, average power consumption as well as latency constraints. When FOVs are homogeneous, we obtain a closed-form expression for the optimal joint policy which reveals interesting communications-caching-computing tradeoffs. When FOVs are heterogeneous, we obtain a local optima of the problem by transforming it into a linearly constrained indefinite quadratic problem and then applying concave convex procedure. Numerical results demonstrate the proposed mobile VR delivery framework can significantly reduce communication bandwidth while meeting low latency requirement.

Communications, Caching, and Computing for Mobile Virtual Reality: Modeling and Tradeoff

The recent rise of interest in Virtual Reality (VR) came with the availability of commodity commercial VR prod- ucts, such as the Head Mounted Displays (HMD) created by Oculus and other vendors. To accelerate the user adoption of VR headsets, content providers should focus on producing high quality immersive content for these devices. Similarly, multimedia streaming service providers should enable the means to stream 360 VR content on their platforms. In this study, we try to cover different aspects related to VR content representation, streaming, and quality assessment that will help establishing the basic knowledge of how to build a VR streaming system.

Streaming Virtual Reality Content

We study an approach to tweet classification based on distant supervision, whereby we automatically transfer labels from one social medium to another. In particular, we apply classes assigned to YouTube videos to tweets linking to these videos. This provides for free a virtually unlimited number of labelled instances that can be used as training data. The experiments we have run show that a tweet classifier trained via these automatically labelled data substantially outperforms an analogous classifier trained with a limited amount of manually labelled data.

/pdf/distant-supervision-for-tweet-classification-using-youtube-2oy0ajrgwo.pdf

Distant Supervision for Tweet Classification Using YouTube Labels

We report our work in the real-time ad hoc search task of TREC2013 Microblog track. Our system focuses on improving retrieval effectiveness of Microblog search through query expansion and reranking of search results. We apply web-based query expansion algorithm for enriching the microblog queries with additional terms from concurrent webpages related to the search topic. Later we apply results reranking through utilizing state-of-the-art learning to rank algorithms to train 12 different ranking models using relevance judgment of Tweets2011-12 queries, for which we conduct feature engineering, validation dataset selection, and the ensemble of these models. Our approach differs from salient approaches in the previous Microblog tracks that are based on document expansion utilizing embedded URLs and that leverage some single ranking model for tweets re-ranking. Our pipeline constructed using the hybrid of these two components showed promising retrieval results on Tweets2013 benchmark dataset.

/pdf/qcri-at-trec-2013-microblog-track-3yvg3w2xf9.pdf

QCRI at TREC 2013 Microblog Track

Re-ranking was shown to have positive impact on the effectiveness for microblog search. Yet existing approaches mostly focused on using a single ranker to learn some better ranking function with respect to various relevance features. Given various available rank learners (such as learning to rank algorithms), in this work, we mainly study an orthogonal problem where multiple learned ranking models form an ensemble for re-ranking the retrieved tweets than just using a single ranking model in order to achieve higher search effectiveness. We explore the use of query-sensitive model selection and rank fusion methods based on the result lists produced from multiple rank learners. Base on the TREC microblog datasets, we found that our selection-based ensemble approach can significantly outperform using the single best ranker, and it also has clear advantage over the rank fusion that combines the results of all the available models.

/pdf/ranking-model-selection-and-fusion-for-effective-microblog-55u87qf9ts.pdf

Ranking model selection and fusion for effective microblog search

Microblog retrieval has received much attention in recent years due to the wide spread of social microblogging platforms such as Twitter. Many research studies investigated different approaches for microblog retrieval. Query expansion is one of the approaches that showed stable performance for improving microblog retrieval effectiveness. In this paper we comprehensively investigate query expansion for microblog retrieval using pseudo relevance feedback (PRF) with different configurations. In addition, we propose a hyperlink-extended PRF by expanding queries using embedded hyperlinks in retrieved microblogs. Our experimental results on TREC microblog data showed that PRF alone could outperform many retrieval approaches if configured properly. Results also showed that utilizing hyperlinked documents in tweets for query expansion improves results over traditional PRF. Our best results achieved using hyperlink-extended PRF outperformed most of the reported results using other approaches.

https://fount.aucegypt.edu/cgi/viewcontent.cgi?article=2209&context=etds

Tarek El-Ganainy

Papers

Streaming Virtual Reality Content

Distant Supervision for Tweet Classification Using YouTube Labels

QCRI at TREC 2013 Microblog Track

Ranking model selection and fusion for effective microblog search

Hyperlink-extended pseudo relevance feedback for improved microblog retrieval