scholarly journals In the mood: the dynamics of collective sentiments on Twitter

2016 ◽  
Vol 3 (6) ◽  
pp. 160162 ◽  
Author(s):  
Nathaniel Charlton ◽  
Colin Singleton ◽  
Danica Vukadinović Greetham
Keyword(s):  
Large Dataset ◽  
Agent Based ◽  
Positive Sentiment ◽  
External Events ◽  
Twitter Users ◽  
Negative Sentiment ◽  
Scoring Algorithms ◽  
The Relationship ◽  
Structurally Stable ◽  
Average User

We study the relationship between the sentiment levels of Twitter users and the evolving network structure that the users created by @-mentioning each other. We use a large dataset of tweets to which we apply three sentiment scoring algorithms, including the open source S enti S trength program. Specifically we make three contributions. Firstly, we find that people who have potentially the largest communication reach (according to a dynamic centrality measure) use sentiment differently than the average user: for example, they use positive sentiment more often and negative sentiment less often. Secondly, we find that when we follow structurally stable Twitter communities over a period of months, their sentiment levels are also stable, and sudden changes in community sentiment from one day to the next can in most cases be traced to external events affecting the community. Thirdly, based on our findings, we create and calibrate a simple agent-based model that is capable of reproducing measures of emotive response comparable with those obtained from our empirical dataset.

scholarly journals Analysing User Experience of Mobile Banking Applications in Nigeria: A Text Mining Approach

2021 ◽  
Vol 12 (No. 1) ◽  
pp. 77-108
Author(s):  
Babatunde S. Omotosho
Keyword(s):  
User Experience ◽  
Commercial Banks ◽  
Mobile Banking ◽  
Effective Manner ◽  
Textual Data ◽  
Positive Sentiment ◽  
Mobile Banking Applications ◽  
Operational Failures ◽  
Negative Sentiment ◽  
Average User

This paper analyses textual data mined from 37,460 reviews written by mobile banking application users in Nigeria over the period November 2012 – July 2020. On a scale of 1 to 5 (5 being the best), the average user rating for the twenty-two apps included in our sample is 3.5; with the apps deployed by non-interest banks having the highest average rating of 4.0 and those by commercial banks with national authorisation having the least rating of 3.4. Results from the sentiment analysis reveal that the share of positive sentiment words (17.8%) in the corpus more than double that of negative sentiment words (7.7%). Furthermore, we find that about 66 per cent of the emotions expressed by the users are associated with ‘trust’, ‘anticipation’, and ‘joy’ while the remaining 34 per cent relate to ‘surprise’, ‘fear’, ‘anger’, and ‘disgust’. These results imply that majority of the users are satisfied with their mobile banking experience. Finally, we find that the main topics contained in the user reviews pertain to (i) feedback on banks’ responsiveness to user complaints (ii) user experience regarding app functionalities and updates, and (iii) operational failures associated with the use of the apps. These results highlight the need for banks to continue to promote awareness of existing functionalities on their apps, educate users on how those solutions could be accessed, and respond to user feedback in a timely and effective manner.

Tracking Public Attitudes toward COVID-19 Vaccination on Tweets in Canada: Using Aspect-based Sentiment Analysis (Preprint)

2021 ◽  
Author(s):  
Hyeju Jang ◽  
Emily Rempel ◽  
Ian Roe ◽  
Giuseppe Carenini ◽  
Naveed Zafar Janjua
Keyword(s):  
Public Health ◽  
Sentiment Analysis ◽  
Vaccine Hesitancy ◽  
Public Health Response ◽  
Major Barrier ◽  
Positive Sentiment ◽  
Twitter Users ◽  
Key Aspects ◽  
Negative Sentiment ◽  
Health Experts

BACKGROUND The development and approval of COVID-19 vaccines have generated optimism for the end of the COVID-19 pandemic and a return to normalcy. However, vaccine hesitancy, often fueled by misinformation poses a major barrier to achieving herd immunity. OBJECTIVE We aim to investigate Twitter users’ attitudes toward COVID-19 vaccination in Canada after vaccine rollout. METHODS We applied a weakly-supervised aspect-based sentiment analysis (ABSA) technique on COVID-19 vaccination-related tweets in Canada. Automatically-generated aspect and opinion terms were manually corrected by public health experts to ensure the accuracy of the terms and make them more domain-specific. Then, based on these manually corrected terms, the system inferred sentiments toward the aspects. We observed sentiments toward key aspects related to COVID-19 vaccination, and investigated how sentiment toward “vaccination” changed over time. In addition, we analyzed the most retweeted/liked tweets by observing most frequent nouns and sentiments toward key aspects. RESULTS After training tweets using an ABSA system, we obtained 108 aspect terms (e.g., “immunity” and “pfizer”) and 6,793 opinion terms (e.g., “trustworthy” for the positive sentiment and “jeopardize” for the negative sentiment). While manually verifying/editing these terms, our public health experts selected 20 key aspects related to COVID-19 vaccination for more analysis. The results showed that the top-ranked automatically-extracted aspects include “risk”, “delay”, and “hope”. The sentiment analysis results for the 20 key aspects revealed negative sentiments related to “vaccine distribution”, “side effects”, “allergy”, “reactions” and “anti-vaxxer”, and positive sentiments related to “vaccine campaign”, “vaccine candidates”, and “immune response”. All these results indicate that the Twitter users express concerns about the safety of vaccines, but still consider vaccines as the option to end the pandemic. In addition, compared to the sentiment of all the tweets, the most retweeted/liked tweets showed more positive sentiment overall, especially about vaccination itself. When looking more closely, the most retweeted/liked tweets showed an interesting dichotomy in Twitter users, i.e., the “anti-vaxxer” population who used a negative sentiment as a means to discourage vaccination and the “Covid Zero” population who used negative sentiments to encourage vaccinations while critiquing the public health response. CONCLUSIONS This study is the first to examine public sentiments toward COVID-19 vaccination on tweets over an extended period of time in Canada. Our findings could inform public health agencies to design and implement interventions to promote vaccination, and get closer to the goal of ending the pandemic.

scholarly journals Emoji Emotional States: Classification on the Valence and Arousal Axes

2021 ◽  
Author(s):  
Gaku Kutsuzawa ◽  
Hiroyuki Umemura ◽  
Koichiro Eto ◽  
Yoshiyuki Kobayashi
Keyword(s):  
Online Survey ◽  
Research Field ◽  
Negative Bias ◽  
Emotional States ◽  
Point Scale ◽  
Positive Sentiment ◽  
Valence And Arousal ◽  
The One ◽  
Negative Sentiment ◽  
The Relationship

Abstract Emojis are frequently used by people worldwide as a tool to express one’s emotional states, and have recently been applied to the research field to assess the same. However, the details of how they correspond to the human emotional states remain unidentified. Thus, this study aimed to understand how emojis are classified on the valence and arousal axes, and to examine the relationship between the former and the human emotional states. In an online survey of 1,082 participants, a nine-point scale was employed to evaluate the valence and arousal levels of 74 facial emojis. The cluster analysis revealed these emojis to be categorized into six different clusters on the two axes of valence and arousal. Further, the one-way analysis of variance indicated these clusters as having six valence and three arousal levels. From these results, each cluster was interpreted as (1) a strong negative sentiment, (2) a moderately negative sentiment, (3) a neutral sentiment with negative bias, (4) a neutral sentiment with positive bias, (5) a moderately positive sentiment, and (6) a strong positive sentiment. Therefore, facial emojis were found to comprehensively express the human emotional states.

scholarly journals Understanding public opinion to the introduction of minimum unit pricing in Scotland: a qualitative study using Twitter

BMJ Open ◽  
2019 ◽  
Vol 9 (6) ◽  
pp. e029690 ◽  
Author(s):  
Laurence Astill Wright ◽  
Su Golder ◽  
Adam Balkham ◽  
J McCambridge
Keyword(s):  
Public Opinion ◽  
Thematic Analysis ◽  
Media Analysis ◽  
Alcohol Policy ◽  
Social Media Analysis ◽  
Policy Issues ◽  
Related Individuals ◽  
Positive Sentiment ◽  
Twitter Users ◽  
Unit Pricing

ObjectivesOn 1 May 2018 minimum unit pricing (MUP) of alcohol was introduced in Scotland. This study used Twitter posts to quantify sentiment expressed online during the introduction of MUP, conducted a thematic analysis of these perceptions and analysed which Twitter users were associated with which particular sentiments.Design and settingThis qualitative social media analysis captured all tweets relating to MUP during the 2 weeks after the introduction of the policy. These tweets were assessed using a mixture of human and machine coding for relevance, sentiment and source. A thematic analysis was conducted.Participants74 639 tweets were collected over 14 days. Of these 53 574 were relevant to MUP.ResultsStudy findings demonstrate that opinion on the introduction of MUP in Scotland was somewhat divided, as far as is discernible on Twitter, with a slightly higher proportion of positive posts (35%) than negative posts (28%), with positive sentiment stronger in Scotland itself. Furthermore, 55% of positive tweets/retweets were originally made by health or alcohol policy-related individuals or organisations. Thematic analysis of tweets showed some evidence of misunderstanding around policy issues.ConclusionsIt is possible to appreciate the divided nature of public opinion on the introduction of MUP in Scotland using Twitter, the nature of the sentiment around it and the key actors involved. It will be possible to later study how this changes when the policy becomes more established.

scholarly journals Trends in Patient, Physician, and Public Perception of Ulnar Collateral Ligament Reconstruction Using Social Media Analytics

2021 ◽  
Vol 9 (3) ◽  
pp. 232596712199005
Author(s):  
Jonathan S. Yu ◽  
James B. Carr ◽  
Jacob Thomas ◽  
Julianna Kostas ◽  
Zhaorui Wang ◽  
...  
Keyword(s):  
Social Media ◽  
Public Perception ◽  
Ulnar Collateral Ligament ◽  
Return To Play ◽  
Social Media Analytics ◽  
Care Providers ◽  
Collateral Ligament ◽  
The Past ◽  
Positive Sentiment ◽  
Negative Sentiment

Background: Social media posts regarding ulnar collateral ligament (UCL) injuries and reconstruction surgeries have increased in recent years. Purpose: To analyze posts shared on Instagram and Twitter referencing UCL injuries and reconstruction surgeries to evaluate public perception and any trends in perception over the past 3 years. Study Design: Cross-sectional study. Methods: A search of a 3-year period (August 2016 and August 2019) of public Instagram and Twitter posts was performed. We searched for >22 hashtags and search terms, including #TommyJohn, #TommyJohnSurgery, and #tornUCL. A categorical classification system was used to assess the sentiment, media format, perspective, timing, accuracy, and general content of each post. Post popularity was measured by number of likes and comments. Results: A total of 3119 Instagram posts and 267 Twitter posts were included in the analysis. Of the 3119 Instagram posts analyzed, 34% were from patients, and 28% were from providers. Of the 267 Twitter posts analyzed, 42% were from patients, and 16% were from providers. Although the majority of social media posts were of a positive sentiment, over the past 3 years, there was a major surge in negative sentiment posts (97% increase) versus positive sentiment posts (9% increase). Patients were more likely to focus their posts on rehabilitation, return to play, and activities of daily living. Providers tended to focus their posts on education, rehabilitation, and injury prevention. Patient posts declined over the past 3 years (–28%), whereas provider posts increased substantially (110%). Of posts shared by health care providers, 4% of posts contained inaccurate or misleading information. Conclusion: The majority of patients who post about their UCL injury and reconstruction on social media have a positive sentiment when discussing their procedure. However, negative sentiment posts have increased significantly over the past 3 years. Patient content revolves around rehabilitation and return to play. Although patient posts have declined over the past 3 years, provider posts have increased substantially with an emphasis on education.

scholarly journals Theoretical and Methodological Approaches to Ecological Changes, Social Behaviour and Human Intergroup Tolerance 300,000 to 30,000 BP

2021 ◽  
Vol 28 (1) ◽  
pp. 53-75 ◽  
Author(s):  
Penny Spikins ◽  
Jennifer C. French ◽  
Seren John-Wood ◽  
Calvin Dytham
Keyword(s):  
Social Behaviour ◽  
Environmental Variability ◽  
Raw Materials ◽  
Modern Human ◽  
Resource Exploitation ◽  
Agent Based ◽  
Advantages And Disadvantages ◽  
Ecological Changes ◽  
The Relationship ◽  
Social Behaviours

AbstractArchaeological evidence suggests that important shifts were taking place in the character of human social behaviours 300,000 to 30,000 years ago. New artefact types appear and are disseminated with greater frequency. Transfers of both raw materials and finished artefacts take place over increasing distances, implying larger scales of regional mobility and more frequent and friendlier interactions between different communities. Whilst these changes occur during a period of increasing environmental variability, the relationship between ecological changes and transformations in social behaviours is elusive. Here, we explore a possible theoretical approach and methodology for understanding how ecological contexts can influence selection pressures acting on intergroup social behaviours. We focus on the relative advantages and disadvantages of intergroup tolerance in different ecological contexts using agent-based modelling (ABM). We assess the relative costs and benefits of different ‘tolerance’ levels in between-group interactions on survival and resource exploitation in different environments. The results enable us to infer a potential relationship between ecological changes and proposed changes in between-group behavioural dynamics. We conclude that increasingly harsh environments may have driven changes in hormonal and emotional responses in humans leading to increasing intergroup tolerance, i.e. transformations in social behaviour associated with ‘self-domestication’. We argue that changes in intergroup tolerance is a more parsimonious explanation for the emergence of what has been seen as ‘modern human behaviour’ than changes in hard aspects of cognition or other factors such as cognitive adaptability or population size.

Re-designation of Ethnic Muslims as Bosniaks in Montenegro

2016 ◽  
Vol 31 (1) ◽  
pp. 137-157
Author(s):  
Mehmed Đečević ◽  
Danijela Vuković-Ćalasan ◽  
Saša Knežević
Keyword(s):  
Twentieth Century ◽  
Social Constructivism ◽  
Continuous Exposure ◽  
Slow Dynamics ◽  
Muslim Population ◽  
Elite Theory ◽  
Analogous Process ◽  
Positive Sentiment ◽  
Comparison Of The Results ◽  
The Relationship

The purpose of this article is to analyse the dynamics of the process of re-designation of ethnic Muslims as Bosniaks in Montenegro. Through a comparison with the analogous process in Serbia, certain specificities are indicated in the context of Montenegro. In line with the premises of the elite theory, we point to the divergent influence of the socially engaged members of the Slavic Muslim cultural corpus in Montenegro on the process of ethnic self-identification of Slavic Muslims in the country. The willingness of a part of this corpus to adhere to the views of the elite part of the population that opposed the ethnonym “Bosniak,” and insisted on retaining the ethnic designation “Muslim,” is interpreted through the lens of social constructivism. The article indicates the formation of the socio-political constructs of “Montenegrin” and “Muslim” that occurred in the last decade of the twentieth century. These two constructs are interlinked; the former is superior as it has ethnic and ethical-political semantic layers, while the latter is subordinate, and it partially stems from the positive sentiment of Slavic Muslims towards Montenegro as the country they inhabit. The relationship between these constructs interferes with the process of accepting national Bosniakhood in a part of the Muslim population in Montenegro. A comparison of the results from the last two population censuses in Montenegro indicates a trend of acceptance of the ethnonym “Bosniak” among the Slavic Muslim population in Montenegro. However, given the slow dynamics of the process, affected by the continuous exposure to factors that increase its complexity, national divergence of Slavic Muslims in Montenegro will most likely prevail.

Investigating the Relationship Between Trust and Sentiment Agreement in Arab Twitter Users

2017 ◽  
pp. 236-245
Author(s):  
Areeb Alowisheq ◽  
Nora Alrajebah ◽  
Asma Alrumikhani ◽  
Ghadeer Al-Shamrani ◽  
Maha Shaabi ◽  
...  
Keyword(s):  
Twitter Users ◽  
The Relationship

scholarly journals Data assimilation in Agent-based models using creation and annihilation operators

2019 ◽  
Author(s):  
Daniel Tang
Keyword(s):  
Real World ◽  
Null Model ◽  
The State ◽  
Actual State ◽  
Agent Based Models ◽  
Agent Based ◽  
Predator Prey ◽  
Predator Prey Model ◽  
The One ◽  
The Relationship

Agent-based models are a powerful tool for studying the behaviour of complex systems that can be described in terms of multiple, interacting ``agents''. However, because of their inherently discrete and often highly non-linear nature, it is very difficult to reason about the relationship between the state of the model, on the one hand, and our observations of the real world on the other. In this paper we consider agents that have a discrete set of states that, at any instant, act with a probability that may depend on the environment or the state of other agents. Given this, we show how the mathematical apparatus of quantum field theory can be used to reason probabilistically about the state and dynamics the model, and describe an algorithm to update our belief in the state of the model in the light of new, real-world observations. Using a simple predator-prey model on a 2-dimensional spatial grid as an example, we demonstrate the assimilation of incomplete, noisy observations and show that this leads to an increase in the mutual information between the actual state of the observed system and the posterior distribution given the observations, when compared to a null model.

scholarly journals Decomposing tourists’ sentiment from raw NL text to assess customer satisfaction

2021 ◽  
pp. 147-151
Author(s):  
Maurizio Romano ◽  
Francesco Mola ◽  
Claudio Conversano
Keyword(s):  
Customer Satisfaction ◽  
Word Of Mouth ◽  
Combined Approach ◽  
Natural Language Text ◽  
Textual Data ◽  
Negative Sentiment ◽  
The Relationship ◽  
Time Information ◽  
Day By Day ◽  
Language Text

The importance of the Word of Mouth is growing day by day in many topics. This phenomenon is evident in everyday life, e.g., the rise of influencers and social media managers. If more people positively debate specific products, then even more people are encouraged to buy them and vice versa. This effect is directly affected by the relationship between the potential customer and the reviewer. Moreover, considering the negative reporting bias is evident in how the Word of Mouth analysis is of absolute interest in many fields. We propose an algorithm to extract the sentiment from a natural language text corpus. The combined approach of Neural Networks, with high predictive power but more challenging interpretation, with more simple but informative models, allows us to quantify a sentiment with a numeric value and to predict if a sentence has a positive (negative) sentiment. The assessment of an objective quantity improves the interpretation of the results in many fields. For example, it is possible to identify crucial specific sectors that require intervention, improving the company's services whilst finding the strengths of the company himself (useful for advertising campaigns). Moreover, considering that the time information is usually available in textual data with a web origin, to analyze trends on macro/micro topics. After showing how to properly reduce the dimensionality of the textual data with a data-cleaning phase, we show how to combine: WordEmbedding, K-Means clustering, SentiWordNet, and the Threshold-based Naïve Bayes classifier. We apply this method to Booking.com and TripAdvisor.com data, analyzing the sentiment of people who discuss a particular issue, providing an example of customer satisfaction.

Sign in / Sign up

Export Citation Format

Share Document