With the rapid growth of online shopping platforms, more and more customers intend to share their shopping experience and product reviews on the Internet. Both large quantity and various forms of online reviews bring difficulties for potential consumers to summary all the heterogenous reviews for reference. This paper proposes a new ranking method through online reviews based on different aspects of the alternative products, which combines both objective and subjective sentiment values. Firstly, weights of these aspects are determined with LDA topic model to calculate the objective sentiment value of the product. During this process, the realistic meaning of each aspect is also summarized. Then, consumers’ personalized preferences are taken into consideration while calculating total scores of alternative products. Meanwhile, comparative superiority between every two products also contributes to their final scores. Therefore, a directed graph model is constructed and the final score of each product is computed by improved PageRank algorithm. Finally, a case study is given to illustrate the feasibility and effectiveness of the proposed method. The result demonstrates that while considering only objective sentiment values of the product, the ranking result obtained by our proposed method has a strong correlation with the actual sales orders. On the other hand, if consumers express subjective preferences towards a certain aspect, the final ranking is also consistent with the actual performance of alternative products. It provides a new research idea for online customer review mining and personalized recommendation.

Service providers — from public institutions to primary care facilities — need to constantly attend to clients’ inquiries to provide useful information and directive guidelines. Ensuring high quality service is challenging as it not only demands detailed domain-specific knowledge, but also the ability to quickly understand the clients’ issues through their diverse — and often casual — descriptions. This paper aims to provide a framework for the development of an automated information broker agent who performs the task of a helper. The main task of the agent is to interact with the client and direct them to obtain further services that cater their personalized need. To do so, the agent should accomplish a sequence of tasks that include natural language inquiry, knowledge gathering, reasoning, and giving feedback; in this way, it simulates a human helper to engage in interaction with the client. The framework combines a question-answering reasoning mechanism while utilizing domain-specific knowledge base. When the users cannot describe clearly their needs, the system tries to narrow down the possibilities by an iterative question-answering process, until it eventually identifies the target. In realizing our framework, we make a proof-of-concept project, Mandy, a primary care chatbot system created to assist healthcare staffs by automating the patient intake process. We describe in detail the system functionalities and design of the system, and evaluate our proof-of-concept on benchmark case studies.

We measure and predict states of Activation and Happiness using a body sensing application connected to smartwatches. Through the sensors of commercially available smartwatches we collect individual mood states and correlate them with body sensing data such as acceleration, heart rate, light level data, and location, through the GPS sensor built into the smartphone connected to the smartwatch. We polled users on the smartwatch for seven weeks four times per day asking for their mood state. We found that both Happiness and Activation are negatively correlated with heart beats and with the levels of light. People tend to be happier when they are moving more intensely and are feeling less activated during weekends. We also found that people with a lower Conscientiousness and Neuroticism and higher Agreeableness tend to be happy more frequently. In addition, more Activation can be predicted by lower Openness to experience and higher Agreeableness and Conscientiousness. Lastly, we find that tracking people’s geographical coordinates might play an important role in predicting Happiness and Activation. The methodology we propose is a first step towards building an automated mood tracking system, to be used for better teamwork and in combination with social network analysis studies.

Modern China is undergoing a variety of social conflicts as the arrival of new era with the transformation of the principal contradiction. Then monitoring the society stable is a huge workload. Online societal risk perception is acquired by mapping on-line public concerns respectively into societal risk events including national security, economy & finance, public morals, daily life, social stability, government management, and resources & environment, and then provides one kind of measurement toward the society state. Obviously, stable and harmonious social situations are the basic guarantee for the healthy development of the stock market. Thus we concern whether the variations of the societal risk are related to stock market volatility. We study their relationships by two steps, first the relationships between search trends and societal risk perception; next the relationships between societal risk perception and stock volatility. The weekend and holiday effects in China stock market are taken into consideration. Three different econometric methods are explored to observe the impacts of variations of societal risk on Shanghai Composite Index and Shenzhen Composite Index. 3 major findings are addressed. Firstly, there exist causal relations between Baidu Index and societal risk perception. Secondly, the perception of finance & economy, social stability, and government management has distinguishing effects on the volatility of both Shanghai Composite Index and Shenzhen Composite Index. Thirdly, the weekend and holiday effects of societal risk perception on the stock market are verified. The research demonstrates that capturing societal risk based on on-line public concerns is feasible and meaningful.

Gushes of Internet public opinions may trigger unexpected incidents that significantly affect social security and stability, especially for ones caused by the failure of public policies. Therefore, forecasting this kind of Internet public opinions is of great significance. The duration could be cited as one of the most direct indicators that can reflect the severity of a specific Internet public opinion case. Based on this background, this paper aims to find the factors that may affect the duration of Internet public opinions, and accordingly proposes a model that can accurately predict the duration before the release of public policies. Specifically, an index system including 8 factors by considering four dimensions, namely, object, environment, reality (offline), and the network (online), is established. In addition, based on the dataset containing 23 typical Internet public opinion cases caused by the failure of public policies, 9 prediction models are gained by applying the multivariate linear regression model, multivariate nonlinear regression model, and the Cobb-Douglas function.

This paper studies how to determine task allocation schemes according to the status and requirements of various teams, to achieve optimal performance for a knowledge-intensive team (KIT), which is different from traditional task assignment. The way to allocate tasks to a team affects task processing and, in turn, influences the team itself after the task is processed. Considering the knowledge requirement of tasks as a driving force and that knowledge exchange is pivotal, we build a KIT system model based on complex adaptive system theory and agent modeling technology, design task allocation strategies (TASs) and a team performance measurement scale utilizing computational experiment, and analyze how different TASs impact the different performance indicators of KITs. The experimental results show the recommend TAS varies under different conditions, such as the knowledge levels of members, team structures, and tasks to be assigned, particularly when the requirements to the team are different. In conclusion, we put forward a new way of thinking and methodology for real task allocation problems and provide support for allocation decision makers.

When people try to decide to buy or not to, they are often influenced by both their inherent opinions and the social marketing activities e.g. advertising, social news with strong point of view. Then people will make their final choice, or even convince other people to buy. After all, this is the brand acceptance formation process. Factually, the dynamics of brand acceptance is essentially an interwoven dynamics of endogenous opinion dynamics disturbed by an information diffusion process. To have a better understanding of the dynamics of brand acceptance, we propose and analyze a coupled agent-based dynamic model that combines the Majority-Rule-based Voter model in opinion dynamics with the SI Model for information spreading to analyze the dynamics of brand acceptance in social media. We focus on two important parameters in diffusion dynamics: the decayed transmission rate (β) and the diffusion frequency (f). When the system is stable, the order parameter of the system is the duration time (τ). In the absence of opinion interaction, the simulation results indicate that, when a brand tries to occupy a larger market share through social marketing approaches, it is always effective to let the opponent to be the propaganda target. While with the Majority-Rule-based Voter Model included, we observe that the opinion interaction could have a dual function, which shows that a brand holding a small market share in the first place needs to adopt diverse marketing approaches according to different marketing environment types.

Time series forecasting research area mainly focuses on developing effective forecasting models to improve prediction accuracy. An ensemble model composed of autoregressive integrated moving average (ARIMA), artificial neural network (ANN), restricted Boltzmann machines (RBM), and discrete wavelet transform (DWT) is presented in this paper. In the proposed model, DWT first decomposes time series into approximation and detail. Then Khashei and Bijari’s model, which is an ensemble model of ARIMA and ANN, is applied to the approximation and detail to extract their both linear and nonlinear components and fit the relationship between the components as a function instead of additive relationship. Furthermore, RBM is used to perform pre-training for generating initial weights and biases based on inputs feature for ANN. Finally, the forecasted approximation and detail are combined to obtain final forecasting. The forecasting capability of the proposed model is tested with three well-known time series: sunspot, Canadian lynx, exchange rate time series. The prediction performance is compared to the other six forecasting models. The results indicate that the proposed model gives the best performance in all three data sets and all three measures (i.e. MSE, MAE and MAPE).