Product reviews are valuable for upcoming buyers in helping them make decisions. To this end, different opinion mining techniques have been proposed, where judging a review sentence's orientation (e.g., positive or negative) is one of their key challenges. Recently, deep learning has emerged as an effective means for solving sentiment classification problems. A neural network intrinsically learns a useful representation automatically without human efforts. However, the success of deep learning highly relies on the availability of large-scale training data. We propose a novel deep learning framework for product review sentiment classification which employs prevalently available ratings as weak supervision signals. The framework consists of two steps: (1) learning a high level representation (an embedding space) which captures the general sentiment distribution of sentences through rating information; and (2) adding a classification layer on top of the embedding layer and use labeled sentences for supervised fine-tuning. We explore two kinds of low level network structure for modeling review sentences, namely, convolutional feature extractors and long short-term memory. To evaluate the proposed framework, we construct a dataset containing 1.1M weakly labeled review sentences and 11,754 labeled review sentences from Amazon. Experimental results show the efficacy of the proposed framework and its superiority over baselines.

As an essential role in smart city applications, personalized recommender systems help users to find their potentially interested items from their historically generated data. Recently, researchers have started to utilize the massive user-generated multi-modal contents to improve recommendation performance. However, previous methods have at least one of the following drawbacks: (1) employing shallow models, which cannot well capture high-level conceptual information; (2) failing to capture personalized user visual preference. In this work, we present a deep Users' Multi-modal Preferences based Recommendation (UMPR) method to capture the textual and visual matching of users and items for recommendation. We extract textual matching from historical reviews. We construct users' visual preference embeddings to model users' visual preference and match them with items' visual embeddings to obtain the visual matching. We apply UMPR on two applications related to smart city: restaurant recommendation and product recommendation. Experiments show that UMPR outperforms competitive baseline methods.

In this letter, an optimal time allocation scheme is proposed to improve the throughput of energy harvesting based backscatter communication. The base station (BS) serving as the power supply is transmitting continuously with constant power. All the relays can harvest radio frequency (RF) energy from the transmission of BS while the user performs backscatter transmission, and then the selected relay decodes and forwards the information from user with harvested RF energy. We propose an optimal time allocation scheme that considers the adaptive backscatter coefficient and relay selection to maximize throughput. Simulation results demonstrate that the proposed scheme outperforms the benchmark strategies in system throughput improvement.