Sentiment Analysis on Social Media Big Data With Multiple Tweet Words

Maheswari, S. Uma; Dhenakaran, S. S.

doi:10.35940/ijitee.j9684.0881019

Cited by 7 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the present research, different supervised machine learning has been developed, resulting in a comparative analysis for the selection of the most accurate and effective algorithm for the built dataset. In the study, the predicted sentiment polarity for a given tweet is either classified as positive or negative, as developed by Maheswari and Dhenakaran (2019). For the feature vector formation required as an input for these machine learning classification algorithms, the training dataset is transformed into a bag of words where each entry corresponds to the number of occurrences of a particular term in the sentence (Soumya and Pramod, 2020).…”

Section: Methodsmentioning

confidence: 99%

Empowerment of women's entrepreneurship in family business through Twitter

González-Tejero

Cano-Marin

2022

JFBM

View full text Add to dashboard Cite

PurposeThe main purpose is to provide a global understanding of the role of women in entrepreneurship and family businesses, enabling the evaluation of the impact and the sentiment their role generates. To this end, empowerment and businesswomen's positioning through user-generated content (UCG) on Twitter is assessed.Design/methodology/approachThe research is carried out from a quantitative and qualitative perspective through the evaluation of UGC from the social platform Twitter. A total of 37,852 tweets have been collected and subsequently analysed about the role of entrepreneurial women. For that purpose, a set of supervised machine learning algorithms have been developed for sentiment analysis, as a natural language processing (NLP) technique, outlining random forest as the one with the highest accuracy. Finally, social network analysis (SNA) techniques and graph theory are applied to a generated text-to-network, which enables the identification of the most relevant topics in the discussion.FindingsThe results revealed a positive relationship in the sentiment of the generated content in relation to women entrepreneurs and leaders. An increasing trend was evidenced in the number of published tweets, as well as in the identified topics, highlighting the needs and challenges faced by women in the business environment as the most widely discussed.Research limitations/implicationsThe study develops both theoretical and practical implications so that the findings result in applications in academia and society. The performed analysis creates consciousness about the challenges of women in society, specifically in entrepreneurship.Originality/valueThe study contributes to further enriching the literature on women's entrepreneurship by addressing UGC via Twitter around the role of women, entrepreneurship and power positions.

show abstract

Section: Methodsmentioning

confidence: 99%

Empowerment of women's entrepreneurship in family business through Twitter

González-Tejero

Cano-Marin

2022

JFBM

View full text Add to dashboard Cite

show abstract

“…Semua data yang dihasilkan tersebut kebanyakan berasal dari aplikasi media sosial seperti We Chat, Twitter, Facebook dan Instargram yang memiliki jumlah pengguna yang sangat besar dan tersebar diseluruh dunia. Aplikasi social media telah menjadi bagian dari kehidupan sehari-hari dari orang-orang yang secara terus-menerus berbagi pendapat mereka tentang hidup, informasi, pengetahuan, minat dan sebagainya dalam setiap detiknya [3]. Data dari media sosial menjadi sumber penemuan pengetahuan terbesar dan banyak digunakan bidang analitik big data dengan berbagai metode dan teknik [4].…”

Section: Pendahuluanunclassified

Analitik Big Data: Social Media Mining

Rahmala

Ardhito

Riska

2022

ceritaj

View full text Add to dashboard Cite

he development of big data from year to year has become very rapid in line with the development of the Internet of Things (IoT). One of the most widely owned and frequently used devices is a mobile phone, especially a smartphone. Social media applications found on smartphones generate large amounts of data every second. These data are widely used forresearch in various fields of big data analytics. And the techniques used also vary depending on the dataset and the purpose of the research. This study aims to discuss big data analytics, especially social media mining, and some of its techniques for analysis. The research was conducted using a literature review method on journals and books discussing topics relevant to this research. The expected benefit of this research is that it can add insight and knowledge for readers who are interested in the topic of social media mining.

show abstract

“…The pre-processing stage extracts the semantics, syntax, lengthened, metaphor, etc. Studies have shown that around the world 70% of the internet people use lengthened words for different purposes [22], [23], [24].…”

Section: Introductionmentioning

confidence: 99%

Improving Sentiment Analysis in Social Media by Handling Lengthened Words

et al. 2023

View full text Add to dashboard Cite

Machines are continually being channelized in the current era of automation to deliver accurate interpretations of what people communicate on social media. The human species is today engulfed in the concept of what and how people believe, and the decisions made as a result are mostly dependent on the sway of the masses on social media platforms. The usage of internet as well as social media is booming day by day. Today, this ocean of data can be used for the fruitful purposes. Analysis of social media sentiment textual posts can supply knowledge and information that can be used in citizen opinion polling, business intelligence, social contexts, and Internet of Things (IOT)-mood triggered devices. In this manuscript, the main focus is the sentiment analysis based on Emotional Recognition (ER). The proposed system highlights the process of gaining actual sentiment or mood of a person. The key idea to this system is posed by the fact that if smile and laughter can be two different categories of being happy, then why not happpyyyyyy and happy. A novel lexicon based system is proposed that considers the lengthened word as it is, instead of being omitted or normalized. The aggregated intensified senti-scores of lengthened words are calculated using framed lexicon rules. After that, these senti-scores of lengthened words are used to calculate the level of sentiment of the person. The dataset used in this paper is the informal chats happened among different friend groups over Facebook, Tweets and personal chat. The performance of proposed system is compared with traditional systems that ignore lengthened words and proposed system outperform tradition systems by achieving 81% to 96% F-measure rate for all datasets.

show abstract

Sentiment Analysis on Social Media Big Data With Multiple Tweet Words

Cited by 7 publications

References 6 publications

Empowerment of women's entrepreneurship in family business through Twitter

Empowerment of women's entrepreneurship in family business through Twitter

Analitik Big Data: Social Media Mining

Improving Sentiment Analysis in Social Media by Handling Lengthened Words

Contact Info

Product

Resources

About