Predicting the Lifespan and Retweet Times of Tweets Based on Multiple Feature Analysis

Bae, Yongjin; Ryu, Pum-Mo; Kim, Hyunki

doi:10.4218/etrij.14.0113.0657

Cited by 22 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The investigational outcomes show that the proposed model produces satisfactory accuracy in predicting quantity of re-tweets in micro-blogs. Yongjin Bae et al [3] presented a new approach for forecasting the re-tweet times of posts, creditability of tweet and life span of tweets. Authors extracted the information from re-tweet graphs such as number of times re-tweeted, content features and tweet behavior.…”

Section: Related Workmentioning

confidence: 99%

“…Along these lines, it is of extraordinary practical importance to examine and investigate the re-tweet practices for improving the data spread and user involvement in micro blogs. Among the some micro blogs, Twitter is one of the best in proliferating information continuously, and the propagation adequacy of a tweet is associated to the number of times the message has been re-tweeted [3]. Re-tweet forecast is a basic and critical task in micro-blogs as it might impact the procedure of information discussion.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

User Connectivity and Event Popularity Based Re-Tweet Prediction in Social Networks

Sucharitha*,

Vijayalata,

Prasad

2020

IJITEE

View full text Add to dashboard Cite

In recent times, social network services speedup the information proliferation among user groups, leaving the customary media such as newspaper, TV, discussion, web journals, and online interfaces far behind. Different messages are spread rapidly and broadly by re-tweeting in micro-blogs. Foreseeing re-tweet behavior is incredibly challenging because of different reasons. Existing forecasting models basically overlook sociological information and they don’t acquire complete benefit of these emerging factors, influencing the performance of anticipation. In addition, the poorness of re-tweet data also seriously upsets the performance of these approaches. In this article, we take Sina micro-blog for instance, intending to anticipate the probable quantity of re-tweets of an original tweet as per the time series dispersion of its top n re-tweets. So as to deal with the above issue, we present the idea of a tweet life-cycle, which is essentially calculated by three parameters called the reaction-time, content-significance, interim-time circulation, and afterward the given time series dispersion arch of its top n re-tweets is fitted by a two-stage function, in order to foresee the quantity of its re-tweets in specific time period. The stages in the function are partitioned by the life-cycle of the original tweet and various functions are utilized in the two stages. We have assessed our methodology on real-world data-set; moreover contrast our outcomes with baseline methods. Our examinations prove that the proposed methodology can precisely anticipate the quantity of future re-tweets for a particular tweet.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

User Connectivity and Event Popularity Based Re-Tweet Prediction in Social Networks

Sucharitha*,

Vijayalata,

Prasad

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…Activity refers to the extent of user participation through posting messages. Users who are active on Twitter tend to have their messages read and retweeted by others (Bae, et al, 2014). However, some prior research has found the converse to be true, possibly due to the problem of information overload (Stieglitz & Linh, 2013).…”

Section: Hypothesis 2a: User's Connectivity Affects Retransmission Outcomesmentioning

confidence: 99%

Rumor Retransmission on Twitter: Message Characteristics, user Characteristics and Retransmission Outcomes

Chua¹,

Chen²

2019

Journal of Digital Information Management

View full text Add to dashboard Cite

This paper seeks to depict online rumor retransmission using three main constructs, namely, message characteristics, user characteristics and retransmission outcomes. In particular, it teases retransmission outcomes into volume, immediacy and lifespan of rumor tweets. The dataset was drawn from 322 original Twitter messages which generated some 5,700 retweets about the rumored death of Lee Kuan Yew (LKY). Content analysis and statistical tests were conducted. The results confirm the robustness of the research model. Specifically, rumor message characteristics affect retransmission in terms of volume, immediacy and lifespan. Additionally, user characteristics are positively related to volume and immediacy. Finally, user characteristics have a moderating effect on the relationships between rumor message characteristics and retransmission outcomes. This paper illustrates the applicability of the information diffusion model on online rumor retransmission which hitherto has yet to be attempted. Moreover, it granularizes the concept of online rumor retransmission into three important outcomes, namely, volume, immediacy and lifespan. On the practical front, this paper has implications for organizations seeking to combat rumors.

show abstract

“…Through predicting whether or not a message will be retweeted and the volume of retweets a particular message will receive in the near future, they successfully predicted popularity of messages with good performance. Bae et al [24] extracted tweets with similar topics, retweeting patterns, and properties based on social, local, and content features to make a prediction which achieved significant results. Tsur and Rappoport [25] combined content features with temporal and topological features to predict the spread of an idea in a given time frame via a hybrid approach based on a linear regression.…”

Section: Related Workmentioning

confidence: 99%

A Multidimensional Nonnegative Matrix Factorization Model for Retweeting Behavior Prediction

Wang

Zuo

Wang

2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Today microblogging has increasingly become a means of information diffusion via user’s retweeting behavior. As a consequence, exploring on retweeting behavior is a better way to understand microblog’s transmissibility in the network. Hence, targeted at online microblogging, a directed social network, along with user-based features, this paper first built content-based features, which consisted of URL, hashtag, emotion difference, and interest similarity, based on time series of text information that user posts. And then we measure relationship-based factor in social network according to frequency of interactions and network structure which blend with temporal information. Finally, we utilize nonnegative matrix factorization to predict user’s retweeting behavior from user-based dimension and content-based dimension, respectively, by employing strength of social relationship to constrain objective function. The results suggest that our proposed method effectively increases retweeting behavior prediction accuracy and provides a new train of thought for retweeting behavior prediction in dynamic social networks.

show abstract

Predicting the Lifespan and Retweet Times of Tweets Based on Multiple Feature Analysis

Cited by 22 publications

References 12 publications

User Connectivity and Event Popularity Based Re-Tweet Prediction in Social Networks

User Connectivity and Event Popularity Based Re-Tweet Prediction in Social Networks

Rumor Retransmission on Twitter: Message Characteristics, user Characteristics and Retransmission Outcomes

A Multidimensional Nonnegative Matrix Factorization Model for Retweeting Behavior Prediction

Contact Info

Product

Resources

About