scholarly journals Haters vs. lovers on Facebook

2021 ◽  
Vol 12 (1) ◽  
pp. 27-48
Author(s):  
Milica Vučković
Keyword(s):  
Content Analysis ◽  
Sentiment Analysis ◽  
Response Rate ◽  
Barack Obama ◽  
Top Down ◽  
Negative Sentiment

This paper tries to answer what is the dominant sentiment of comments that users leave on the Facebook fan pages of politicians in power. To answer this question, first the auto-code sentiment analysis of nearly 44,000 comments posted on the Facebook fan page of former US president Barack Obama was conducted. Secondly, content analysis was conducted on 2,411 comments posted on former Croatian president Ivo Josipović’s Facebook fan page. The results of auto-code sentiment analysis showed that examined comments in Obama’s case were mostly neutral and positive, while negative sentiment was the least represented in Obama’s case. The results of content analysis in the Croatian case revealed that the dominant sentiment of all comments was also positive. Finally, it was revealed that the response rate in both cases was zero, what tells us that Obama and Josipović used Facebook only for top-down communication, while the interactive potential of Facebook was neglected.

Document Preprocessing with TF-IDF to Improve the Polarity Classification Performance of Unstructured Sentiment Analysis

2020 ◽  
pp. 235-242
Author(s):  
Farrikh Alzami ◽  
Erika Devi Udayanti ◽  
Dwi Puji Prabowo ◽  
Rama Aria Megantara
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Random Forest ◽  
Sentiment Analysis ◽  
Classification Performance ◽  
Document Preparation ◽  
Learning Models ◽  
Polarity Classification ◽  
Negative Sentiment ◽  
Machine Learning Models

Sentiment analysis in terms of polarity classification is very important in everyday life, with the existence of polarity, many people can find out whether the respected document has positive or negative sentiment so that it can help in choosing and making decisions. Sentiment analysis usually done manually. Therefore, an automatic sentiment analysis classification process is needed. However, it is rare to find studies that discuss extraction features and which learning models are suitable for unstructured sentiment analysis types with the Amazon food review case. This research explores some extraction features such as Word Bags, TF-IDF, Word2Vector, as well as a combination of TF-IDF and Word2Vector with several machine learning models such as Random Forest, SVM, KNN and Naïve Bayes to find out a combination of feature extraction and learning models that can help add variety to the analysis of polarity sentiments. By assisting with document preparation such as html tags and punctuation and special characters, using snowball stemming, TF-IDF results obtained with SVM are suitable for obtaining a polarity classification in unstructured sentiment analysis for the case of Amazon food review with a performance result of 87,3 percent.

The Effects of Different Kernels in SVM Sentiment Analysis on Mass Social Distancing

2020 ◽  
Vol 9 (2) ◽  
pp. 161
Author(s):  
Komang Dhiyo Yonatha Wijaya ◽  
Anak Agung Istri Ngurah Eka Karyawati
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Kernel Method ◽  
Idle Time ◽  
Linear Kernel ◽  
Social Distancing ◽  
The Social ◽  
Negative Sentiment ◽  
F Measure ◽  
Kernel Yield

During this pandemic, social media has become a major need as a means of communication. One of the social medias used is Twitter by using messages referred to as tweets. Indonesia currently undergoing mass social distancing. During this time most people use social media in order to spend their idle time However, sometimes, this result in negative sentiment that used to insult and aimed at an individual or group. To filter that kind of tweets, a sentiment analysis was performed with SVM and 3 different kernel method. Tweets are labelled into 3 classes of positive, neutral, and negative. The experiments are conducted to determine which kernel is better. From the sentiment analysis that has been performed, SVM linear kernel yield the best score Some experiments show that the precision of linear kernel is 57%, recall is 50%, and f-measure is 44%

scholarly journals Users’ Experiences With an Interactive Evidence to Decision (iEtD) Framework: A Qualitative Analysis

2020 ◽  
Author(s):  
Jose Francisco Meneses-Echavez ◽  
Sarah Rosenbaum ◽  
Gabriel Rada ◽  
Signe Flottorp ◽  
Jenny Moberg ◽  
...  
Keyword(s):  
Health Care ◽  
Decision Making ◽  
Content Analysis ◽  
Response Rate ◽  
Guideline Development ◽  
Structured Interview ◽  
Positive Experience ◽  
Audio Recordings ◽  
Real Scenario ◽  
Care Decision

Abstract Background: Evidence to Decision (EtD) frameworks bring clarity, structure and transparency to health care decision making. The interactive Evidence to Decision (iEtD) tool, developed in the context of the DECIDE project and published by Epistemonikos, is a stand-alone online solution for producing and using EtD frameworks. Since its development, little is known about how organizations have been using the iEtD tool and what characterizes users’ experiences with it.Methods: This study aimed to describe users’ experiences with the iEtD and identify main barriers and facilitators related to use. We contacted all users registered in the iEtD via email and invited people who identified themselves as having used the solution to a semi-structured interview. Audio recordings were transcribed, and one researcher conducted a content analysis of the interviews guided by a user experience framework. Two researchers checked the content independently for accuracy. Results: Out of 860 people contacted, 81 people replied to our introductory email (response rate 9.4%). Twenty of these had used the tool in a real scenario and were invited to an interview. We interviewed all eight users that accepted this invitation (from six countries, four continents). ‘Guideline development’ was the iEtD use scenario they most commonly identified. Most participants reported an overall positive experience, without major difficulties navigating or using the different sections. They reported having used most of the EtD framework criteria. Participants reported tailoring their frameworks, for instance by adding or deleting criteria, translating to another language, or rewording headings. Several people preferred to produce a Word version rather than working online, due to the burden of completing the framework, or lack of experience with the tool. Some reported difficulties working with the exportable formats, as they needed considerable editing.Conclusion: A very limited number of guideline developers have used the iEtD tool published by Epistemonikos since its development. Although users’ general experiences are positive, our work has identified some aspects of the tool that need improvement. Our findings could be also applied to development or improvement of other solutions for producing or using EtD frameworks.

scholarly journals Analysis of Social Media Users Sentiments against Omnibus Law Based on Hashtags on Twitter

SISTEMASI ◽  
2022 ◽  
Vol 11 (1) ◽  
pp. 197
Author(s):  
Okta Fanny ◽  
Heri Suroyo
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Main Topic ◽  
Accuracy Score ◽  
Test Results ◽  
Bayes Classifier ◽  
The Public ◽  
Average Accuracy ◽  
Positive Sentiment ◽  
Negative Sentiment

From the research that has been done, it can be concluded that Sentiment Analysis can be used to know the sentiment of the public, especially Twitter netizens against omnibus law. After the sentiment analysis, it looks neutral artmen with the largest percentage of 55%, then positive sentiment by 35% and negative sentiment by 10%. The results of the analysis showed that the Naïve Bayes Classifier method provides classification test results with accuracy in Hashtag Pro with an average accuracy score of 92.1%, precision values with an average of 94.8% and recall values with an average of 90.7%. While Hashtag Counter For data classification, with an average accuracy value of 98.3%, precision value with an average of 97.6% and recall value with an average of 98.7%. The result of text cloud analysis conducted on a combination of hashtags both Hashtag pros and Hashtags cons, the dominant word appears is Omnibus Law which means that all hashtags in scrap is really discussing the main topic that is about Omnibus Law

scholarly journals Sentiment Analysis on Government Performance in Tourism During The COVID-19 Pandemic Period With Lexicon Based

CAUCHY ◽  
2021 ◽  
Vol 7 (1) ◽  
pp. 28-39
Author(s):  
Adri Priadana ◽  
Ahmad Ashril Rizal
Keyword(s):  
Sentiment Analysis ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Tourism Industry ◽  
Naive Bayes Classifier ◽  
Bayes Classifier ◽  
Naïve Bayes Classifier ◽  
Trending Topics ◽  
The Government ◽  
Negative Sentiment

The COVID-19 pandemic impact has affected all industries in Indonesia and even the world, including the tourism industry. Researchers have a role in researching to answer the needs of the tourism industry, especially in making tourism and business destination management programs and carrying out activities oriented to meet the needs of the tourism industry. Meanwhile, the government has a role in making policies, especially in the roadmap, for developing the tourism industry. This study aims to track trending topics in social media Instagram since COVID-19 hit. The results of trending topics will be classified by sentiment analysis using a Lexicon-based and Naive Bayes Classifier. Based on Instagram data taken since January 2020, it shows the five highest topics in the tourism sector, namely health protocols, hotels, homes, streets, and beaches. Of the five topics, sentiment analysis was carried out with the Lexicon-based and Naive Bayes classifier, showing that beaches get an incredibly positive sentiment, namely 80.87%, and hotels provide the highest negative sentiment 57.89%. The accuracy of the Confusion matrix's sentiment results shows that the accuracy, precision, and recall are 82.53%, 86.99%, and 83.43%, respectively.

scholarly journals Mining social media data to investigate patient perceptions regarding DMARD pharmacotherapy for rheumatoid arthritis

2020 ◽  
Vol 79 (11) ◽  
pp. 1432-1437 ◽  
Author(s):  
Chanakya Sharma ◽  
Samuel Whittle ◽  
Pari Delir Haghighi ◽  
Frada Burstein ◽  
Roee Sa'adon ◽  
...  
Keyword(s):  
Rheumatoid Arthritis ◽  
Social Media ◽  
Side Effects ◽  
Sentiment Analysis ◽  
Computer Algorithms ◽  
Social Media Platforms ◽  
Synthetic Agents ◽  
Positive Sentiment ◽  
Negative Sentiment ◽  
Media Data

ObjectivesWe hypothesise that patients have a positive sentiment regarding biological/targeted synthetic disease modifying anti-rheumatic drugs (b/tsDMARDs) and a negative sentiment towards conventional synthetic agents (csDMARDs). We analysed discussions on social media platforms regarding DMARDs to understand the collective sentiment expressed towards these medications.MethodsTreato analytics were used to download all available posts on social media about DMARDs in the context of rheumatoid arthritis. Strict filters ensured that user generated content was downloaded. The sentiment (positive or negative) expressed in these posts was analysed for each DMARD using sentiment analysis. We also analysed the reason(s) for this sentiment for each DMARD, looking specifically at efficacy and side effects.ResultsComputer algorithms analysed millions of social media posts and included 54 742 posts about DMARDs. We found that both classes had an overall positive sentiment. The ratio of positive to negative posts was higher for b/tsDMARDs (1.210) than for csDMARDs (1.048). Efficacy was the most commonly mentioned reason in posts with a positive sentiment and lack of efficacy was the most commonly mentioned reason for a negative sentiment. These were followed by the presence/absence of side effects in negative or positive posts, respectively.ConclusionsPublic opinion on social media is generally positive about DMARDs. Lack of efficacy followed by side effects were the most common themes in posts with a negative sentiment. There are clear reasons why a DMARD generates a positive or negative sentiment, as the sentiment analysis technology becomes more refined, targeted studies could be done to analyse these reasons and allow clinicians to tailor DMARDs to match patient needs.

Sentiment annotations for reviews: an information quality perspective

2018 ◽  
Vol 42 (5) ◽  
pp. 579-594 ◽  
Author(s):  
Heng-Li Yang ◽  
August F.Y. Chao
Keyword(s):  
Sentiment Analysis ◽  
Information Quality ◽  
Future Research ◽  
Content Type ◽  
Sentence Level ◽  
Product Service ◽  
Alternative Approach ◽  
Internet Information ◽  
Negative Sentiment ◽  
Practical Implications

Purpose The purpose of this paper is to propose sentiment annotation at sentence level to reduce information overloading while reading product/service reviews in the internet. Design/methodology/approach The keyword-based sentiment analysis is applied for highlighting review sentences. An experiment is conducted for demonstrating its effectiveness. Findings A prototype is built for highlighting tourism review sentences in Chinese with positive or negative sentiment polarity. An experiment results indicates that sentiment annotation can increase information quality and user’s intention to read tourism reviews. Research limitations/implications This study has made two major contributions: proposing the approach of adding sentiment annotation at sentence level of review texts for assisting decision-making; validating the relationships among the information quality constructs. However, in this study, sentiment analysis was conducted on a limited corpus; future research may try a larger corpus. Besides, the annotation system was built on the tourism data. Future studies might try to apply to other areas. Practical implications If the proposed annotation systems become popular, both tourists and attraction providers would obtain benefits. In this era of smart tourism, tourists could browse through the huge amount of internet information more quickly. Attraction providers could understand what are the strengths and weaknesses of their facilities more easily. The application of this sentiment analysis is possible for other languages, especially for non-spaced languages. Originality/value Facing large amounts of data, past researchers were engaged in automatically constructing a compact yet meaningful abstraction of the texts. However, users have different positions and purposes. This study proposes an alternative approach to add sentiment annotation at sentence level for assisting users.

scholarly journals Textbooks, Postcards, and the Public Consolidation of Nationalism in Latin America

2020 ◽  
Vol 43 (4) ◽  
pp. 515-542
Author(s):  
Anna Kyriazi ◽  
Matthias vom Hau
Keyword(s):  
Twentieth Century ◽  
Latin America ◽  
Content Analysis ◽  
Methodological Approach ◽  
Public Life ◽  
Top Down ◽  
The Public ◽  
National Ideology ◽  
Market Driven ◽  
Popular Nationalism

Abstract The existing macro-historical scholarship tends to assert rather than demonstrate the wider impact of nationalism. Yet, state-sponsored national ideologies permeate the broader reaches of society to varying degrees. To investigate variations in the consolidation of official nationalism, this paper combines the content analysis of school textbooks as state-regulated and picture postcards as primarily market-driven sources. Building on this novel methodological approach, we find that textbooks published in mid-twentieth-century Argentina, Mexico, and Peru promoted a similar popular nationalism that portrayed the lower classes as “true” national subjects. However, picture postcards from the same period demonstrate that the consolidation of this official national ideology varied. In Mexico and Peru, the new state-sponsored conceptions of nationhood gained presence in public life, but they did not to take hold in Argentina. We conclude that studying the top-down nationalist messages promoted by states should not be equated with studying their ideological impact in public life.

Sign in / Sign up

Export Citation Format

Share Document