Mining Social Capital on Online Social Networks with Strong and Weak Ties

Alhazmi, Huda; Gokhale, Swapna S.

doi:10.1109/obd.2016.9

Cited by 2 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Text mining is a process of extracting or searching for information to extract knowledge from textual data sources [14]. This method is often used to analyze and understand large amounts of text automatically, allowing the identification of patterns, trends, and knowledge that is difficult or impractical if conducted manually [15]. Some of the main aspects of text mining include information retrieval, text parsing, entity recognition, sentiment analysis, text classification, text grouping, information extraction, topic modeling, text recommendation.…”

Section: B Text Miningmentioning

confidence: 99%

Analysis of Twitter User Sentiment on Presidential Candidate Anies Baswedan Using Naïve Bayes Algorithm

Setiawan,

Dewi

2023

Ilk. J. Ilm.

View full text Add to dashboard Cite

Indonesian hold presidential election in 2024. One of the most discussed topics by public is the presidential candidates. The discussion about the presidential candidate certainly reaped various kinds of responses from public, ranging from support to statements of disapproval. This research was limited to the candidacy of Anies Baswedan as a presidential candidate before a vice president candidate as his pair was selected. The purpose of this study is to conduct a sentiment analysis of public responses regarding Indonesia 2024 presidential candidate Anies Baswedan using tweets data from October 2022 to January 2023 using the naïve bayes classifier algorithm. This is expected to provide an overview of the public opinions on Twitter. Three test models were carried out with differences in the division of the amount of training data and test data, respectively 60%:40%, 70%:30% and 80%:20%. The test results showed the highest accuracy level was obtained by the 3rd model using training and testing data of 80%:20% with an accuracy value of 76.21%. Further research is recommended to conduct sentiment analysis on the pairs of Presidential and Vice-Presidential candidates who have been officially registered with the General Election Commission using various other classification algorithms.

show abstract

Section: B Text Miningmentioning

confidence: 99%

Analysis of Twitter User Sentiment on Presidential Candidate Anies Baswedan Using Naïve Bayes Algorithm

Setiawan,

Dewi

2023

Ilk. J. Ilm.

View full text Add to dashboard Cite

show abstract

“…In fact, Granovetter's definition of tie strength makes a reference to the 'reciprocal services which characterize a tie' as a factor in building, maintaining, and measuring tie strength (Granovetter, 1973). Reciprocity has been linked to SNS members' common ground (Pai & Arnott, 2013), which is a significant factor of tie strength, while the mutual exchange of wall posts has been used for the computational calculation of tie strength in data mining studies (Alhazmi & Gokhale, 2016). Furthermore, if we consider question asking as a form of selfdisclosure, since the fact that one is interested in something is information about them, then eliciting answers to questions on SNSs also constitutes disclosure with an expectation of reciprocity.…”

Section: Tie Strengthmentioning

confidence: 99%

Altruistic and selfish communication on social media: the moderating effects of tie strength and interpersonal trust

Spiliotopoulos

Oakley

2019

Behaviour & Information Technology

View full text Add to dashboard Cite

Individuals share a diversity of content on social media for a variety of reasons. Research has often described and explained disclosure via the application of a subjective cost-benefit analysis framed around reciprocity, suggesting that people communicate selfishly motivated by the expectation of receiving something in return. This paper investigates the moderating effects of tie strength and interpersonal trust on the relationship between expected reciprocity and intensity of communication between two social media connections. A Facebook application presented participants with a random set of their friends and asked them to rate their friendships in terms of these values. Overall, 90 participants rated 1728 friendships, while the application collected 11 activity variables depicting the actual communication that has taken place in each pair of connections. A principal component analysis was used to distinguish between text-and photograph-related communication, and two moderated multiple regressions were conducted to establish the moderating effects. The results show significant moderating effects of tie strength and trust on the communication around photographs, but not around text. This study contributes to communication research by explicating the ways that tie strength and trust affect patterns of communication on social media. Implications for social media researchers and designers are discussed.

show abstract

Mining Social Capital on Online Social Networks with Strong and Weak Ties

Cited by 2 publications

References 33 publications

Analysis of Twitter User Sentiment on Presidential Candidate Anies Baswedan Using Naïve Bayes Algorithm

Analysis of Twitter User Sentiment on Presidential Candidate Anies Baswedan Using Naïve Bayes Algorithm

Altruistic and selfish communication on social media: the moderating effects of tie strength and interpersonal trust

Contact Info

Product

Resources

About