People use Online Social Networks (OSNs) to express their opinions and feelings about many topics. Depending on the nature of an event and its dissemination rate in OSNs, and considering specific regions, the users' behavior can drastically change over a specific period of time. In this context, this work aims to propose an event detection system at the early stages of an event based on changes in the users' behavior in an OSN. This system can detect an event of any subject, and thus, it can be used for different purposes. The proposed event detection system is composed of the following main modules: (1) determination of the user's location, (2) message extraction from an OSN, (3) topic identification using natural language processing (NLP) based on the Deep Belief Network (DBN), (4) the user behavior change analyzer in the OSN, and (5) affective analysis for emotion identification based on a tree-convolutional neural network (tree-CNN). In the case of public health, the early event detection is very relevant for the population and the authorities in order to be able take corrective actions. Hence, the new coronavirus disease (COVID-19) is used as a case study in this work. For performance validation, the modules related to the topic identification and affective analysis were compared with other similar solutions or implemented with other machine learning algorithms. In the performance assessment, the proposed event detection system achieved an accuracy higher than 0.90, while other similar methods reached accuracy values less than 0.74. Additionally, our proposed system was able to detect an event almost three days earlier than the other methods. Furthermore, the information provided by the system permits to understand the predominant characteristics of an event, such as keywords and emotion type of messages. INDEX TERMS Event detection, Online Social Networks, affective analysis, natural language processing, COVID-19.

No abstract

The neotropical genus Physalaemus Fitzinger is currently composed by 48 species (Cardozo & Pereyra 2018). Recently, a phylogenetic analysis aiming to investigate the internal relationships of the genus recovered two major clades, the Physalaemus cuvieri and P. signifer clades (Lourenço et al. 2015). The following species groups were retrieved in the first clade: P. biligonigerus, P. cuvieri, P. gracilis, P. henselii, and P. olfersii groups (Lourenço et al. 2015). This proposal redefined the P. olfersii group including P. olfersii (Lichtenstein & Martens), P. soaresi Izecksohn, P. maximus Feio, Pombal, & Caramaschi, P. feioi Cassini, Cruz, & Caramaschi and P. lateristriga (Steindachner). The authors also allocated tentatively P. orophilus Cassini, Cruz, & Caramaschi, and P. insperatus Cruz, Cassini, & Caramaschi in the P. olfersii group due to their morphological similarity with the other species (Cruz et al. 2008; Cassini et al. 2010). Otherwise, Physalaemus aguirrei Bokermann was not recovered nested within this group, contradicting what was suggested in a previous phenetic analysis (Nascimento et al. 2005). Members of the P. olfersii group inhabit the Atlantic rainforest and most of them have a similar advertisement calls with pulsed notes, without frequency modulation and harmonic structure (Giaretta et al. 2009; Cassini et al. 2010; Lourenço et al. 2015). Regarding their larval stage, only P. soaresi, P. maximus, and P. olfersii have their tadpoles described (Weber et al. 2005; Baêta et al. 2007; Giaretta et al. 2009). Physalaemus orophilus occurs in montane Atlantic Forest sites at the eastern slope of the Espinhaço Range in the State of Minas Gerais, southeastern Brazil (Cassini et al. 2010). Herein, we describe the tadpole of P. orophilus from Quadrilátero Ferrífero mountain region, southern limit of the Espinhaço Range and compared it to the known tadpoles of the P. olfersii group.

The traffic volume of video streaming service has increased considerably in recent years due to the success of content distributors such as YouTube and Netflix. However, limitations in network capacity and instability, impact the user Quality of Experience (QoE). In this work, a quality assessment model for video streaming service is proposed and implemented in mobile devices. The proposed model considers the spatial degradations of the video frames and the temporal interruptions. The experimental results show the impact of degradation factors on the user's QoE; emphasizing that the proposed model achieved a high correlation with subjective tests. Furthermore, the implementation on the mobile device has a low consumption in both processing capacity and energy.