An explainable sentiment prediction model based on the portraits of users sharing representative opinions in social sensors

“Social sensors” refer to those who provide opinions through electronic communication channels such as social networks. There are two major issues in current models of sentiment analysis in social sensor networks. First, most existing models only analyzed the sentiment within the text but did not analyze the users, which led to the experimental results difficult to explain. Second, few studies extract the specific opinions of users. Only analyzing the emotional tendencies or aspect-level emotions of social users brings difficulties to the analysis of the opinion evolution in public emergencies. To resolve these issues, we propose an explainable sentiment prediction model based on the portraits of users sharing representative opinions in social sensors. Our model extracts the specific opinions of the user groups on the topics and fully considers the impacts of their diverse features on sentiment analysis. We conduct experiments on 51,853 tweets about the “COVID-19” collected from 1 May 2020 to 9 July 2020. We build users’ portraits from three aspects: attribute features, interest features, and emotional features. Six machine learning algorithms are used to predict emotional tendency based on users’ portraits. We analyze the influence of users’ features on the sentiment. The prediction accuracy of our model is 64.88%.

A Framework for Identifying Influential People by Analyzing Social Media Data

In this paper, we introduce a new framework for identifying the most influential people from social sensor networks. Selecting influential people from social networks is a complicated task as it depends on many metrics like the network of friends, followers, reactions, comments, shares, etc. (e.g., friends-of-a-friend, friends-of-a-friend-of-a-friend). Data on social media are increasing day-by-day at an enormous rate. It is also a challenge to store and process these data. Towards this goal, we use Hadoop to store data and Apache Spark for the fast computation of the data. To select influential people, we apply the mechanisms of skyline query and top-k query. To the best of our knowledge, this is the first work to apply the Apache Spark framework to identify influential people on social sensor network, such as online social media. Our proposed mechanism can find influential people very quickly and efficiently on the data pattern of Facebook.

Infoveillance based on Social Sensors to Analyze the impact of Covid19 in South American Population

ABSTRACTInfoveillance is an application from Infodemiology field with the aim to monitor public health and create public policies. Social sensor is the people providing thought, ideas through electronic communication channels(i.e. Internet). The actual scenario is related to tackle the covid19 impact over the world, many countries have the infrastructure, scientists to help the growth and countries took actions to decrease the impact. South American countries have a different context about Economy, Health and Research, so Infoveillance can be a useful tool to monitor and improve the decisions and be more strategical. The motivation of this work is analyze the capital of Spanish Speakers Countries in South America using a Text Mining Approach with Twitter as data source. The preliminary results helps to understand what happens two weeks ago and opens the analysis from different perspectives i.e. Economics, Social.

Participatory Social Sensor: A Framework to Social Media Data Acquisition and Analysis

Nowadays, understanding urban mobility, transit, people viewpoint, and social behaviors has been the focus of many research and investments. However, data access is restricted to private companies and governments. In addition, the costs to create a sensor infrastructure on a given area is prohibitive. Then, using Location-Based Social Media (LBSM) may provide a new way to better comprehend the social behaviors, by the use of a users viewpoint. In this work, we propose the use of LBSM as participatory sensing, designing the Participatory Social Sensor (PSS), a friendly framework to social media data acquisition and analysis. We develop the Twitter data acquisition and analysis process, aiming to achieve the user application goals through a file setup,where the user specifies the spatial area, temporal interval, tags, and other parameters. As a result, the PSS shows a set of visual analysis which provides a context overview, allowing an easy way to researchers make-decision. A case study, Detection and Enrichment Service for Road Events Based on Heterogeneous Data Merger for VANETs, based on PSS framework was published in the current conference.

Transmission Optimization of Social and Physical Sensor Nodes via Collaborative Beamforming in Cyber-Physical-Social Systems

The recently emerging cyber-physical-social system (CPSS) can enable efficient interactions between the social world and cyber-physical system (CPS). The wireless sensor network (WSN) with physical and social sensor nodes plays an important role in CPSS. The integration of the social sensors and physical sensors in CPSS provides an advantage for smart services in different application areas. However, the dynamics of social mobility for social sensors pose new challenges for implementing the coordination of transmission. Furthermore, the integration of social and physical sensors also faces the challenges in term of improving energy efficiency and increasing transmission range. To solve these problems, we integrate the model of social dynamics with collaborative beamforming (CB) technique to formulate the transmission optimization problem as a dynamic game. A novel transmission scheme based on reinforcement learning is proposed to solve the formulated problem. The corresponding implementation of the proposed transmission scheme in CPSS is presented by the design of message exchange processes. The extensive simulation results demonstrate that the proposed transmission scheme presents lower interference to noise ratio (INR) and better signal to noise ratio (SNR) performance in comparison with the existing schemes. The results also indicate that the proposed method has effective adaptation to the dynamic mobility of social sensor nodes in CPSS.