Browsing by Author "de Matos, Nelson Manuel da Silva"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Multimodal sentiment classifier framework for different scene contextsPublication . Cardoso, Pedro; Rodrigues, Joao; de Matos, Nelson Manuel da SilvaSentiment analysis (SA) is an effective method for determining public opinion. Social media posts have been the subject of much research, due to the platforms’ enormous and diversified user bases that regularly share thoughts on nearly any subject. However, on posts composed by a text–image pair, the written description may or may not convey the same sentiment as the image. The present study uses machine learning models for the automatic sentiment evaluation of pairs of text and image(s). The sentiments derived from the image and text are evaluated independently and merged (or not) to form the overall sentiment, returning the sentiment of the post and the discrepancy between the sentiments represented by the text–image pair. The image sentiment classification is divided into four categories—“indoor” (IND), “man-made outdoors” (OMM), “non-man-made outdoors” (ONMM), and “indoor/outdoor with persons in the background” (IOwPB)—and then ensembled into an image sentiment classification model (ISC), that can be compared with a holistic image sentiment classifier (HISC), showing that the ISC achieves better results than the HISC. For the Flickr sub-data set, the sentiment classification of images achieved an accuracy of 68.50% for IND, 83.20% for OMM, 84.50% for ONMM, 84.80% for IOwPB, and 76.45% for ISC, compared to 65.97% for the HISC. For the text sentiment classification, in a sub-data set of B-T4SA, an accuracy of 92.10% was achieved. Finally, the text–image combination, in the authors’ private data set, achieved an accuracy of 78.84%.
- Technological transformation: the importance of E-WOM and perceived privacy in the context of opinion platformsPublication . Gelashvili, Vera; Martínez-Navalón, Juan Gabriel; de Matos, Nelson Manuel da Silva; Correia, Marisol B.Opinion platforms are the result of technological advances that have increased the importance for users to check other users' opinions about products and services before making a purchase. The aim of this research paper is twofold: (i) to analyse whether there is a direct and positive relationship between the privacy of Google Maps users and variables such as satisfaction and trust, and (ii) whether the E-WOM of Google Maps is related to the satisfaction and trust of its users. To achieve the objectives of the study, a questionnaire was collected from users of Google Maps reviews in Spain. A total of 375 valid responses were analysed using PLS-SEM methodology. In particular, structural model analysis was used for the formative and reflective variables. This study sheds new light on opinion platforms and their usefulness for efficient business management, as well as specifying the importance of user privacy for their satisfaction. The importance of E-WOM for user satisfaction, trust and privacy is emphasised. The findings underline the importance of technological advances for different stakeholders and society. This study reduces the gap in the usefulness of opinion platforms, especially Google Maps, and contributes to the academic literature on the variables studied.
- The online destination image as portrayed by the user-generated content on social media and its impact on tourists' engagementPublication . Martins Guerreiro, Maria Manuela; Ramos, Celia; de Matos, Nelson Manuel da Silva; Golestaneh, Seyed Homayoun; Sequeira, Bernardete; Nobre Pereira, Luis; MIGUEL AGAPITO, DORA LÚCIA; Rafaela Martins; Wikesjö, MagdaTourism Destination Image (TDI) is complex, dynamic and multidimensional by nature and shaped by a multitude of events, interactions and sensory impressions, especially once the tourist is at the destination, generating tourists' engagement on social media networks. This study aims to measure the online destination image (ODI) portrayed in user-generated content (UGC) on social media by employing the sentiment analysis method. Data were extracted from Facebook and Instagram on the Visit Algarve social media profile. The Algarve region is situated in the south of Portugal and is one of Europe's most popular tourist destinations. The main results shed light on the relevance of intangible heritage experiences as triggers of positive feelings about the destination. Content shared about tourists' activities in the region generates more engagement in the tourism destination's social media. Tangible heritage received the lowest rated sentiment, and destination agents should strategically look into it as there are opportunities for destination management. Tourism infrastructure has the lowest engagement value; therefore, in terms of promotion, it does not generate interest.