Sentiment Analysis to Assess the Community’s Enthusiasm Towards the Development Chatbot Using an Appraisal Theory

Widyaningrum, Prima; Ruldeviyani, Yova; Dharayani, Ramanti

doi:10.1016/j.procs.2019.11.176

Cited by 17 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The afinn algorithm was developed by Finn Arup Nielsen as the Afinn Word Database, and extended by analyzing Twitter posts, and it contains slang and words used on the web. Scores are equal or above +5 for positive words and equal or below -5 for the negative ones (Naldi, 2019;Widyaningrum et al, 2019). All these methods assign a score (from negative to positive) to the words which compose tweets and the score for every tweet is the algebraic sum of the word's scores.…”

Section: Methodsmentioning

confidence: 99%

The Perceptions of Migration During the Pandemic: What Twitter Data Tell Us?

Miccoli¹,

Ambrosetti

2023

Migration Letters

View full text Add to dashboard Cite

This paper aims to analyse sentiments and emotions about migration in Italy using Twitter, by comparing the period of COVID-19 pandemic with the previous year. We take Italy as a case study because it has been severely affected by the COVID-19, it is one of the largest recipients of immigrants in Europe and, is among the few countries that implemented an amnesty for irregular migrant workers during the pandemic. We apply a text mining and sentiment analysis to the tweets with hashtags and keywords related to the migration and to the COVID-19 pandemic. Results show that tweets related to migration express a sense of emergency and also invasion. No major changes occurred in the period of the pandemic in comparison with the previous period. Indeed, both negative and positive sentiments are present in the tweets in both periods, confirming a certain polarization in the public discourse about migration.

show abstract

Section: Methodsmentioning

confidence: 99%

The Perceptions of Migration During the Pandemic: What Twitter Data Tell Us?

Miccoli¹,

Ambrosetti

2023

Migration Letters

View full text Add to dashboard Cite

show abstract

“…reporting positive or negative words), and emotional categorization into the following eight types: anger, anticipation, disgust, fear, joy, sadness, surprise, trust, positive, negative. Syuzhet natural language processing has been applied to several sources of data and was found reliable (Ragupathy and Maguluri, 2018; Widyaningrum et al, 2019; Yoon et al, 2017). Grounded in the Interactive-Constructive-Active-Passive (ICAP) framework that suggests that arguing a position is the highest level of cognitive engagement (Chi et al, 2018), we tracked elementary units of argumentative discourse.…”

Section: Methodsmentioning

confidence: 99%

Interactions between emotional and cognitive engagement with science on YouTube

Dubovi

Tabak

2021

Public Underst Sci

View full text Add to dashboard Cite

This study aimed to map and characterize public engagement with science on YouTube. A two-part study was conducted. First, we collected and quantitatively analyzed trending videos on YouTube to evaluate the magnitude of public interaction with science content. Then, we assessed actual, rather than self-reports of, media interactions with science-related YouTube trending videos. We tested associations between behavioral engagement of viewing, liking, disliking or commenting, and emotional and cognitive engagement. Our findings affirm that science content attracts high public interest and that emotional and cognitive engagement with science on social media are distinct, but interrelated. We show that regardless of the valence of emotional engagement, emotion is linked to greater behavioral engagement of posting comments and to greater cognitive engagement of argumentative deliberation. Therefore, our findings suggest that social media interactions, which tend to evoke emotional responses, are a promising means of advancing person-to-person engagement with science.

show abstract

“…It allows one to measure the polarity of the attitudes expressed in a text. Its use facilitates better decision-making on public opinions, in addition to providing valuable information, especially in the analysis of social networks [ 48 , 49 ]. There are three kinds of polarity: negative, neutral, and positive.…”

Section: Methodsmentioning

confidence: 99%

“…There are three kinds of polarity: negative, neutral, and positive. Normally, the analysis systems use a scoring scale, ranging from -1 to 1, where a negative score corresponds to a negative sentiment; zero is considered a neutral sentiment and a positive score corresponds to a positive sentiment [ 48 , 49 , 50 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Confined Students: A Visual-Emotional Analysis of Study and Rest Spaces in the Homes

Cuerdo-Vilches

Martín

2021

IJERPH

View full text Add to dashboard Cite

Confinement was adopted globally as a containment measure to face the COVID pandemic declared by WHO on March 2020. In Spain, the State of Alarm was established for three months. This implied the interruption of educational activities, having a higher incidence for children, since teaching would not be resumed until the following academic year, in September. This, together with the confusing initial information about COVID-19 transmission between children and their families, has made them one of the groups most vulnerable. In this study, a qualitative approach is made to secondary school students (aged 12). They were asked to share their experiences about confinement from the perspective of the home spaces, in relation to two main tasks relevant in this period: the tele-study and their relaxing time and well-being. Using images and narratives with an abstract and emotional description, the response of 46 children was obtained. A sentiment analysis was carried out from their testimonies. Results suggest a greater availability of tele-study spaces with daylighting, mainly in bedrooms, with laptops. For leisure and rest spaces, sofas, beds, and cohabitant gathering were preferred. Written testimonials were mainly positive. Housing features and family cohesion condition their resilience in situations of uncertainty, like confinement.

show abstract

Sentiment Analysis to Assess the Community’s Enthusiasm Towards the Development Chatbot Using an Appraisal Theory

Cited by 17 publications

References 5 publications

The Perceptions of Migration During the Pandemic: What Twitter Data Tell Us?

The Perceptions of Migration During the Pandemic: What Twitter Data Tell Us?

Interactions between emotional and cognitive engagement with science on YouTube

Confined Students: A Visual-Emotional Analysis of Study and Rest Spaces in the Homes

Contact Info

Product

Resources

About