Search results for "Sentiment analysis"
showing 10 items of 46 documents
When a new technological product launching fails: A multi-method approach of facial recognition and E-WOM sentiment analysis
2018
Abstract The dual aim of this research is, firstly, to analyze the physiological and unconscious emotional response of consumers to a new technological product and, secondly, link this emotional response to consumer conscious verbal reports of positive and negative product perceptions. In order to do this, biometrics and self-reported measures of emotional response are combined. On the one hand, a neuromarketing experiment based on the facial recognition of emotions of 10 subjects, when physical attributes and economic information of a technological product are exposed, shows the prevalence of the ambivalent emotion of surprise. On the other hand, a nethnographic qualitative approach of sen…
Analysis and Comparison of Deep Learning Networks for Supporting Sentiment Mining in Text Corpora
2020
In this paper, we tackle the problem of the irony and sarcasm detection for the Italian language to contribute to the enrichment of the sentiment analysis field. We analyze and compare five deep-learning systems. Results show the high suitability of such systems to face the problem by achieving 93% of F1-Score in the best case. Furthermore, we briefly analyze the model architectures in order to choose the best compromise between performances and complexity.
Increasing the Inference and Learning Speed of Tsetlin Machines with Clause Indexing
2020
The Tsetlin Machine (TM) is a machine learning algorithm founded on the classical Tsetlin Automaton (TA) and game theory. It further leverages frequent pattern mining and resource allocation principles to extract common patterns in the data, rather than relying on minimizing output error, which is prone to overfitting. Unlike the intertwined nature of pattern representation in neural networks, a TM decomposes problems into self-contained patterns, represented as conjunctive clauses. The clause outputs, in turn, are combined into a classification decision through summation and thresholding, akin to a logistic regression function, however, with binary weights and a unit step output function. …
Parole, parole, parole. Un’analisi testuale delle canzoni più vendute in Italia (1960-2019)
2023
Questo articolo esplora il contenuto delle cento canzoni italiane più vendute, nel periodo che va dal 1960 al 2019, utilizzando un approccio computazionale inedito che combina analisi testuale e analisi musicale automatica. I brani italiani da classifica hanno intercettato alcuni dei principali trend storici, culturali e sociali degli ultimi sessant’anni. Dalla ricerca emergono sei temi ricorrenti (perdono, fuga, amore passione, fatica, fantasia e vitalità) e due dimensioni di senso latenti (patire vs. agire e divertirsi vs. riflettere), che caratterizzano i testi analizzati. Dal punto di vista metodologico, emerge l’importanza discriminate del sound per comprendere sia il clima emotivo dei…
Systematic Literature Review on Customer Emotions in Social Media
2018
Customers are human beings who express their emotions openly on social media platforms. There is a wealth of social media data that companies can make use of to improve their business decision making and tailor their marketing strategies. In order to benefit from this, organizations need to apply computational methods, which can save time and effort rather than applying traditional consumer research approaches, such as surveys or interviews. The purpose of this study is to investigate existing computational studies on detecting consumer emotions from social media data. We conducted a systematic literature review on articles published in ScienceDirect, IEEE Explore, ACM Digital Library, and …
Cognitive Reasoning and Inferences through Psychologically based Personalised Modelling of Emotions Using Associative Classifiers
2014
The development of Microsoft Kinect opened up the research field of computational emotions to a wide range of applications, such as learning environments, which are excellent candidates to trial computational emotions based algorithms but were never feasible for given consumer technologies. Whilst Kinect is accessible and affordable technology it comes with its' own additional challenges such as the limited number of extracted Action Units (AUs). This paper presents a new approach that attempts at finding patterns of interaction between AUs and each other on one hand and patterns that link the related AUs to a given emotion. In doing so, this paper presents the ground work necessary to reac…
Vaccine Hesitancy on Social Media: Sentiment Analysis from June 2011 to April 2019
2021
Vaccine hesitancy was one of the ten major threats to global health in 2019, according to the World Health Organisation. Nowadays, social media has an important role in the spread of information, misinformation, and disinformation about vaccines. Monitoring vaccine-related conversations on social media could help us to identify the factors that contribute to vaccine confidence in each historical period and geographical area. We used a hybrid approach to perform an opinion-mining analysis on 1,499,227 vaccine-related tweets published on Twitter from 1st June 2011 to 30th April 2019. Our algorithm classified 69.36% of the tweets as neutral, 21.78% as positive, and 8.86% as negative. The perce…
Examining Competing Entrepreneurial Concerns in a Social Question and Answer (SQA) Platform
2021
This study aims to determine the competing concerns of people interested in startup development and entrepreneurship by using topic modeling and sentiment analysis on a social question-and-answer (SQA) website. Understanding the underlying concerns of startup entrepreneurs is critical to society and economic growth. Therefore, greater scientific support for entrepreneurship remains necessary, including data mining from virtual social communities. In this study, an SQA platform was used to identify the sentiment of thirty concerns of people interested in startup entrepreneurship. Based on topic modeling and sentiment analysis of 18819 inquiries in various forums on an SQA, we identified addi…
Samsung and Volkswagen Crisis Communication in Facebook and Twitter : A Comparative Study
2017
Since September 2015 at least two major crises have emerged where major industrial companies producing consumer products have been involved. In September 2015 diesel cars manufactured by Volkswagen turned out to be equipped with cheating software that caused NO2 and other emission values to be reduced to acceptable levels while tested from the real, unacceptable values in normal use. In August 2016 reports began to appear that the battery of a new smart phone produced by Samsung, Galaxy Note7, could begin to burn, or even explode, while the device was on. In Nov. 2016 also 34 washing machine models were reported to have caused damages due to disintegration. In all cases, the companies have …
The Issue Arena of a Corporate Social Responsibility Crisis : The Volkswagen Case in Twitter
2016
This paper explores the online debate in a corporate social responsibility crisis, where multiple actors communicate through social media, each representing different interests and views pertaining to the crisis. The study utilizes Twitter data relating to the recent case of the falsified Volkswagen diesel emissions that became public in 2015. To better understand the online interaction, use is made of issue arena theory and insights on CSR crises. The focus is on capturing the issue as it evolved over time, the actors and sentiments expressed, and the responses of the organization. The findings show that after the case became public, the emissions issue received massive attention in Twitte…