Sentiment and Emotional Analysis of Risk Perception in the Herculaneum Archaeological Park during COVID-19 Pandemic

Abstract

This paper proposes a methodology for sentiment analysis with emphasis on the emotional aspects of people visiting the Herculaneum Archaeological Park in Italy during the period of the COVID-19 pandemic. The methodology provides a valuable means of continuous feedback on perceived risk of the site. A semantic analysis on Twitter text messages provided input to the risk management team with which they could respond immediately mitigating any apparent risk and reducing the perceived risk. A two-stage approach was adopted to prune a massively large dataset from Twitter. In the first phase, a social network analysis and visualisation tool NodeXL was used to determine the most recurrent words, which was achieved using polarity. This resulted in a suitable subset. In the second phase, the subset was subjected to sentiment and emotion mapping by survey participants. This led to a hybrid approach of using automation for pruning datasets from social media and using a human approach to sentiment and emotion analysis. Whilst suffering from COVID-19, equally, people suffered due to loneliness from isolation dictated by the World Health Organisation. The work revealed that despite such conditions, people’s sentiments demonstrated a positive effect from the online discussions on the Herculaneum site.

Using Citizen Science to Manage Odour Emissions in National IED Plants: A Systematic Review of the Scientific Literature

“…Hence, after a proper organization of the answers, they could be elaborated through data mining techniques [81]. Considering the type of data, clustering or natural language processing (NLP) techniques could be applied, as already reported in scientific literature for other purposes (e.g., the sentiment analysis of perceptions about cultural heritage [82], occupational risk assessment [83,84]).…”

Open Source Intelligence Opportunities and Challenges: a Review

“…The authors suggested that the open-source intelligence company involved in this project must understand its data holdings and comply with General Data Protection Regulation obligations. Also, many researchers (for example [81][82][83][84][85]), used OSINT methods and tools for emotional analysis, risk perception and mental health analysis during COVID-19 pandemic. This research was mainly based on social media analysis.…”

Fake News Detection Model on Social Media by Leveraging Sentiment Analysis of News Content and Emotion Analysis of Users’ Comments

“…Sentiment analysis (SA) is one of the sections that belong to the NLP field [ 11 ] and is responsible for designing and applying models, techniques, and approaches to identify whether a text deals with objective or subjective information [ 55 ] and, in the last case, to identify whether that information was expressed in a negative, neutral, or positive manner [ 56 ] as well as whether it is strong or weak [ 26 ]. The SA method is used in many fields, especially in social media [ 57 ], such as classifying users’ opinions on social media posts [ 58 , 59 ], or knowing the tendencies of the masses in elections and predicting the final results, in addition to controlling public opinion by understanding the public’s attitudes by analyzing users’ opinions about certain situations [ 32 ].…”