Search

With the development of the Internet, the content that people share contains types of text, images, and videos, and utilizing these multimodal data for sentiment analysis has become an important area of research. Multimodal sentiment analysis aims to understand and perceive emotions or sentiments in different types of data. Currently, the realm of multimodal sentiment analysis faces various challenges, with a major emphasis on addressing two key issues: (1) inefficiency when modeling the intramodality and intermodality dynamics and (2) inability to effectively fuse multimodal features. In this paper, we propose the CCDA (cross-correlation in dual-attention) model, a novel method to explore dynamics between different modalities and fuse multimodal features efficiently. We capture dynamics at intra- and intermodal levels by using two types of attention mechanisms simultaneously. Meanwhile, the cross-correlation loss is introduced to capture the correlation between attention mechanisms. Moreover, the relevant coefficient is proposed to integrate multimodal features effectively. Extensive experiments were conducted on three publicly available datasets, CMU-MOSI, CMU-MOSEI, and CH-SIMS. The experimental results fully confirm the effectiveness of our proposed method, and, compared with the current optimal method (SOTA), our model shows obvious advantages in most of the key metrics, proving its better performance in multimodal sentiment analysis. [ABSTRACT FROM AUTHOR]

This research presents a new model based on Twitter posts and VADER algorithms to analyze social media discourse during and following a bushfire event. The case study is the Gold Coast community that experienced the first bushfire event of Australia's severe Black Summer in 2019/2020. This study aims to understand which communities and stakeholders generate and exchange information on disasters caused by natural hazards. In doing so, a new methodology to analyze social media in disaster management is presented. This model enables stakeholders to understand key message themes and community sentiment during and following the disaster, as well as the individuals and groups that shape the messaging. Three main findings emerged. Firstly, the results show that messaging volume is a proxy for the importance of the bushfires, with a clear increase during the bushfire event and a sharp decline after the event. Secondly, from a content perspective, there was a consistent negative message sentiment (even during recovery) and the need for better planning, while the links between bushfires and climate change were key message themes. Finally, it was found that politicians, broadcast media and public commentators were central influencers of social media messaging, rather than bushfire experts. This demonstrates the potential of social media to inform disaster response and recovery behavior related to natural hazards. [ABSTRACT FROM AUTHOR]

Nowadays customers would make decisions by reading online reviews and comparing differences in restaurants before visiting. Therefore how restaurants take advantage from such information is important to attract customers and stay competitive. Many researchers believe that increasing business performance could improve competitiveness. However, with changing customer requirements and business environment, it is challenging to understand which attributes matter the most to customers and how to improve considering competitors. Therefore this study proposed assessing restaurant competitiveness using online reviews. After crawling 38,479 online reviews employing Python, deep learning-based BERT is developed to measure attribute performance and understand the competitiveness through McKinsey Matrix. Then, the competitiveness was analyzed from a temporal dynamic view to present how attributes are changing importance. Notably, the asymmetric effects between attribute performance and satisfaction were considered. Results demonstrated encouraging accuracy in measuring restaurant competitiveness and explained how asymmetric McKinsey Matrix could help formulate efficient competitiveness enhancement strategies. • Develops a deep learning-based BERT to accurately assess restaurant competitiveness. • Incorporates asymmetric effects to formulate competitiveness enhancement strategies. • Considers how attributes are changing competition position over temporal dynamics. • Improves McKinsey Matrix for efficient restaurant competitiveness analysis. [ABSTRACT FROM AUTHOR]

In the dynamic field of destination management, maintaining a destination's competitiveness requires understanding the evolving preferences of tourists. However, current research often adopts a static approach, failing to capture the dynamic nature of tourist needs and the evolving competitiveness of a destination. To address this, we introduce a novel approach using user-generated content from various social media platforms over a six-year period to assess key attributes that influence destination competitiveness. The results indicate that attributes in deciding destination competitiveness are not fixed, with some remaining stable factors in competitiveness, while others fluctuate over time. Attributes that even alter their competitive standing could significantly impact overall destination competitiveness. This research contributes a dynamic model that allows destination managers to adapt strategies in real time, aligning with current market conditions and enhancing competitiveness in the tourism industry. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative approach for assessing visitor satisfaction at the destination level by identifying attributes of interest from social media text and indirectly measuring performance and importance values. A lexicon-based method for sentiment analysis is applied to determine performance value at the destination level, while importance is calculated using an adjusted association rule mining algorithm. The results are validated with earlier survey-based attributes relevant to visitors and Australia's case. The results demonstrate encouraging accuracy, suggesting that the proposed methodology offers opportunities to assess tourist satisfaction at destinations with larger sample sizes for a lower cost and greater data collection flexibility than traditional approaches. The methods proposed could be beneficial in a wide range of tourism contexts. • Destinations are recognized from tourists' travel itineraries. • Sentiment analysis is applied to identify performance at multiple destinations. • The importance of each attribute is calculated proportionally at each destination. • Validated results of social media data with survey data [ABSTRACT FROM AUTHOR]

With the growth of smartphone usage the number of social media posts has significantly increased and represents potentially valuable information for management, including of natural resources and the environment. Already, evidence of using ‘human sensor’ in crises management suggests that collective knowledge could be used to complement traditional monitoring. This research uses Twitter data posted from the Great Barrier Reef region, Australia, to assess whether the extent and type of data could be used to Great Barrier Reef organisations as part of their monitoring program. The analysis reveals that large amounts of tweets, covering the geographic area of interest, are available and that the pool of information providers is greatly enhanced by the large number of tourists to this region. A keyword and sentiment analysis demonstrates the usefulness of the Twitter data, but also highlights that the actual number of Reef-related tweets is comparatively small and lacks specificity. Suggestions for further steps towards the development of an integrative data platform that incorporates social media are provided. [ABSTRACT FROM AUTHOR]