Fig 4 - uploaded by Liviu-Adrian Cotfas
Content may be subject to copyright.
![Ontology of emotions [23]](profile/Liviu-Adrian-Cotfas/publication/308893894/figure/fig11/AS:667890218983447@1536248845973/Ontology-of-emotions-23.png)
Source publication
![Figure 1: Ontology for emotion representation used in [19]](profile/Liviu-Adrian-Cotfas/publication/308893894/figure/fig2/AS:414217518764034@1475768560284/Ontology-for-emotion-representation-used-in-19_Q320.jpg)
![Figure 2: Ontology for object – facet representation used in [3]](profile/Liviu-Adrian-Cotfas/publication/308893894/figure/fig9/AS:414217522958336@1475768561053/Ontology-for-object-facet-representation-used-in-3_Q320.jpg)
![Fig. 4. Ontology of emotions [23]](profile/Liviu-Adrian-Cotfas/publication/308893894/figure/fig11/AS:667890218983447@1536248845973/Ontology-of-emotions-23_Q320.jpg)
With the on growing usage of microblogging services, such as Twitter, millions of users share opinions daily on virtually everything. Making sense of this huge amount of data using sentiment and emotion analysis, can provide invaluable benefits to organizations trying to better understand what the public thinks about their services and products. Wh...
Context in source publication
Context 1
... From them, it has been chosen the emotional categories ontology presented in [23], as besides being inspired by recognized psychological models, it also structures the different human emotions in a taxonomy. The nine top-level emotions in the ontol- ogy, as well as the second-level emotions associated with the concept of "Anger", are shown in Fig. 4. The ontology contains for each class a number of individuals, representing words associated with the particular type of emotion. In order to obtain a better coverage of the words used to express emotions, we have chosen to enrich the ontology using some of the values in the corresponding WordNet synsets [24]. Fig. 5. shows the WordNet ...
Citations
... Opinion mining is a growing area of the Natural Language Processing field commonly used to determine viewpoints towards targets of interest using computational methods [27]. It is also known as sentiment analysis and includes many subtasks, such as polarity detectionin which the goal is to determine whether a text has positive, negative or neutral connotation [28], emotion identificationin which the objective is to uncover specific emotions such as happiness, fear or sadness [29], subjectivity detectionin which the goal is to determine if the text is objective or subjective [30]. ...
The coronavirus outbreak has brought unprecedented measures, which forced the authorities to make decisions related to the instauration of lockdowns in the areas most hit by the pandemic. Social media has been an important support for people while passing through this difficult period. On November 9, 2020, when the first vaccine with more than 90% effective rate has been announced, the social media has reacted and people worldwide have started to express their feelings related to the vaccination, which was no longer a hypothesis but closer, each day, to become a reality. The present paper aims to analyze the dynamics of the opinions regarding COVID-19 vaccination by considering the one-month period following the first vaccine announcement, until the first vaccination took place in UK, in which the civil society has manifested a higher interest regarding the vaccination process. Classical machine learning and deep learning algorithms have been compared to select the best performing classifier. 2 349 659 tweets have been collected, analyzed, and put in connection with the events reported by the media. Based on the analysis, it can be observed that most of the tweets have a neutral stance, while the number of in favor tweets overpasses the number of against tweets. As for the news, it has been observed that the occurrence of tweets follows the trend of the events. Even more, the proposed approach can be used for a longer monitoring campaign that can help the governments to create appropriate means of communication and to evaluate them in order to provide clear and adequate information to the general public, which could increase the public trust in a vaccination campaign.
... Ontologies have already been successfully used in many social media analysis tasks, including detecting trending news and topics (Ejaz et al. 2018), modeling of extreme financial events (Qu et al. 2016), understanding people behavior in an earthquake evacuation scenario (Iwanaga et al. 2011), extracting user preferences regarding the characteristics of a product (Kontopoulos et al. 2013), and analyzing the emotions expressed in social media messages (Cotfas et al. 2016). ...
... For representing the first category of concepts, the ones concerning the tweets and their properties, we have chosen to use the ontology described in (Cotfas et al. 2016), which reuses classes and properties from well-known ontologies, as recommended in the ontology modeling best practices (Allemang and Hendler 2011). By reusing concepts and properties from recognized vocabularies such as Dublin Core (prefix dcterms), FOAF (prefix foaf), SIOC (prefix sioc), and Basic Geo WGS84 (prefix geo), the ontology facilitates the integration between the data extracted by analyzing the social media messages and the vast amount of information available in other ontologies, such as the ones included in Linking Open Data Cloud (Linked Data Community 2018). ...
While the literature contains many slightly different definitions for the image of a company, they all put great emphasis on its importance. Many of the messages posted on social media networks nowadays contain strong sentiment and emotion indications regarding almost any topic, therefore turning them into a rich and almost real-time data source for analyzing the public’s opinion on various subjects, including many of the factors that can influence the image of companies. Thus, in this chapter we propose a natural language processing (NLP) approach for monitoring and evaluating the companies’ image by extracting information from social media messages posted on Twitter. The messages are analyzed using a bag-of-words sentiment analysis approach. The results of the analysis are stored as semantically structured data, thus making it possible to fully exploit the possibilities offered by semantic web technologies, such as inference and accessing the vast amount of knowledge in Linked Open Data, for further analysis.
... A semantic web-based approach for analyzing social media users' emotions towards the products and services offered by a company has been proposed in Cotfas et al. (2016). Thanks to using an emotion ontology that structures emotions in a hierarchy, starting from general ones to more particular ones, the public's opinion can be analyzed at different levels of emotions granularity. ...
... In this context, the present paper adapts the approach proposed in Cotfas et al. (2016) with the purpose of analyzing the public's opinion concerning companies from social media messages, with the help of emotion analysis and semantic web technologies. Moreover, the identified perception can be easily analyzed in the context of the business sector to which the company belongs. ...
... Ontologies have already been successfully applied in many social media analysis tasks, including detecting trending news and topics (Ejaz et al. 2018), modeling of extreme financial events (Qu et al. 2016), understanding people behavior in an earthquake evacuation scenario (Iwanaga et al. 2011), analyzing how social media users perceive the products and services offered by companies , as well as their opinions regarding the characteristics of the products and services (Cotfas et al. 2016;. ...
... The information stored in ontologies can easily be retrieved using a specialized query language, known as SPARQL and new relationships inside the data can be discovered through inference using semantic reasoning engines. Ontologies have already been successfully used in many social media analysis tasks, including detecting trending news and topics [13], modelling of extreme financial events [14], understanding people behaviour in an earthquake evacuation scenario [15], extracting user preferences regarding the characteristics of a product [4] and analysing the emotions expressed in social media messages [16]. The concepts required in order to semantically search information in previously collected social media messages can be grouped in the following three categories: concepts that describe the social media specific knowledge; concepts that represent the analysed entities, such as products or service; concepts that provide a connection between the social media messages, the analysed entities, as well as with any other additional data obtained using NLP techniques, such as sentiment or emotion analysis. ...
... For representing the social media concepts and their properties, we have chosen to use the ontology that we have proposed in [16], which extends well recognized ontologies such as SIOC and FOAF with the concepts specific to Twitter and follows the recommended ontology modelling best practices. The tw prefix is used in the following to denote classes or properties belonging to this ontology. ...
... While many sentiment analysis algorithms have been proposed in the scientific literature, we have chosen to use the bag of words model described in [16], given its low complexity and adequate results. ...
... There are considered two sequences of data with non-zero initial values and with the same length, data 0 and , j=1...n ,with t = time period and n = variables [27,31,32]: The absolute degree of grey incidence is: ...
Due to COVID-19 pandemic, public health emergency was created throughout the world. So, we took the base data and perform analysis on how the effect of vaccination on the human lives in terms of recovery, severity, side effects, and deaths on the globe. We also analyzed the country wise vaccination to understand the scenarios in the world, because the COVID virus is transforming in different countries in different ways, therefore the understanding the mutations of the virus and the use of the drug analysis also very much important for the future generations and also useful to face the future COVID virus mutations.
Recent studies have shown that based on informal communication, made from one user to another, certain opinions regarding the activity of a company can be formed, with long-term influence on consumers, perception on its image. By focusing on the Millennial generation, this research presents its main characteristics and examines the consumer’s behaviour in online social networks, with an accent on how his perception towards certain companies may change due to communications on these networks with other users. Based on the latest studies in the literature, a questionnaire has been created, containing most of the issues identified in the publications related directly to consumer behaviour and company’s image. Additionally, a PANAS analysis has been conducted in order to see whether there are any behaviour or opinion differences between the two identified categories of Millennial online social networks’ users: “Enthusiastic” and “Stressed”. In the end, a grey incidence analysis has been applied to the considered variables.
The coronavirus pandemic has forced authorities to take unprecedented measures, including the temporary closure of business and the instauration of national and regional lockdowns. The educational system, one of the key components of the society, has also been disrupted, as many schools and universities have moved their courses online for prolonged periods. With the introduction of the first vaccine on December 8, 2020, social media users have reacted by posting messages supporting or rejecting the vaccination process. In this context, the present paper aims to analyze the opinions regarding COVID-19 vaccination in education-related tweets. A dataset containing 102,805 English tweets published in the month following the beginning of the vaccination process has been collected. Several classical machine learning and deep learning algorithms have been compared and the best-performing classifier, RoBERTa, has been selected and applied for determining the stance of the collected tweets, as in favor, against or neutral. The evolution of the opinions has been put in correspondence with the main events that have occurred during the analyzed period, while the main discussion topics have been outlined using the Latent Dirichlet Allocation and n-gram analysis. The obtained results can be useful for authorities looking to better understand the opinions of the parents, students, teachers, and general public.
Emotion ontologies have been developed to capture affect, a concept that encompasses discrete emotions and feelings, especially for research on sentiment analysis, which analyzes a customer's attitude towards a company or a product. However, there have been limited efforts to adapt and employ these ontologies. This research surveys and synthesizes emotion ontology studies to develop a Framework of Emotion Ontologies that can be used to help a user select or design an appropriate emotion ontology to support sentiment analysis and increase the user's understanding of the roles of affect, context, and behavioral information with respect to sentiment. The framework, which is derived from research on emotion ontologies, psychology, and sentiment analysis, classifies emotion ontologies as discrete emotion or one of two hybrid ontologies that are combinations of the discrete, dimensional, or componential process emotion paradigms. To illustrate its usefulness, the framework is applied to the development of an emotion ontology for a sentiment analysis application.
