Klout score: Measuring influence across multiple social networks

  title={Klout score: Measuring influence across multiple social networks},
  author={Adithya Rao and Nemanja Spasojevic and Zhisheng Li and Trevor DSouza},
  journal={2015 IEEE International Conference on Big Data (Big Data)},
In this work, we present the Klout Score, an influence scoring system that assigns scores to 750 million users across 9 different social networks on a daily basis. [] Key Method The features are scalably generated by processing over 45 billion interactions from social networks every day, as well as by incorporating factors that indicate real world influence.

Figures and Tables from this paper

Analysis of Probabilistic Models for Influence Ranking in Social Networks

The present investigation proceeds with the intuition that interaction is positively correlated with influence and identifies a joint probabilistic model and trains it on interaction characteristics on nodes of a social network for influence ranking.

Exploring Interactions in Social Networks for Influence Discovery

A flexible method is proposed that considers type, quality, quantity and time of reactions and, as a result, the method assesses the influence dependencies within the social network.

Predicting Influential Users in Online Social Network Groups

The Influencers Prediction problem is formulated in the context of groups created in OSNs, and a general framework and an effective methodology to predict which users will be able to influence the behavior of the other ones in a future time period are defined.

Analyzing a User's Contributive Social Capital Based on Acitivities in Online Social Networks and Media

This paper investigated the hypothesis that contributive social capital can be extracted from network properties and networking activity, which were assessed with features such as the number of contributions of each participant, and the prediction of contributivesocial capital showed an improvement over the baseline.

Measuring user influence on Twitter: A survey

AI techniques to analyse a social network on text, user and group level: application on Galaxy2

This article proposes an analysis of 1000 days of activity using NLP techniques to find the most interesting topics and to discover key actors, and proceeds with a MLbased profiling of the user behaviours.

Finding Influentials in Twitter: A Temporal Influence Ranking Model

A PageRank based temporal influence ranking model (TIR) is used to identify influential users and demonstrates that TIR has better performance and is more stable than the existing models in global influence ranking and friend recommendation.

Understanding Popularity, Reputation, and Social Influence in the Twitter Society

It is found that social influence on Twitter is mainly related to popularity rather than reputation, but that this growth of influence with popularity is sublinear and that global network metrics are better predictors of inactivity and social influence.

Social Status and Communication Behavior in an Evolving Social Network

It is shown that individuals with different values of PageRank exhibit different behavior even in early weeks since the online community's inception and it is possible to forecast future PageRank values given frequency of behavioral motifs with high accuracy.

MIDMod-OSN: A Microscopic-level Information Diffusion Model for Online Social Networks

The findings show that followers play an important role in the diffusion process and it is possible to use the diffusion and OSN behavior of users for predicting the trending character of a message without having to count the number of reactions.



LASTA: large scale topic assignment on multiple social networks

This paper presents LASTA (Large Scale Topic Assignment), a full production system used at Klout, Inc., which mines topical interests from five social networks and assigns over 10,000 topics to hundreds of millions of users on a daily basis, and evaluates the topic assignment system on an internal labeled corpus of 32,264 user-topic labels generated from real users.

Social influence analysis in large-scale networks

Topical Affinity Propagation (TAP) is designed with efficient distributed learning algorithms that is implemented and tested under the Map-Reduce framework and can take results of any topic modeling and the existing network structure to perform topic-level influence propagation.

Modelling Influence in a Social Network: Metrics and Evaluation

  • B. HajianT. White
  • Computer Science
    2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing
  • 2011
The hypothesis explored in this paper is that Influence Rank can be quantified based on the interaction between users and their behavior and results supporting the utility of the measure and the accuracy of its estimation using the Page Rank approximation are presented.

Maximizing the spread of influence through a social network

An analysis framework based on submodular functions shows that a natural greedy strategy obtains a solution that is provably within 63% of optimal for several classes of models, and suggests a general approach for reasoning about the performance guarantees of algorithms for these types of influence problems in social networks.

When-To-Post on Social Networks

The personalized schedules derived here are used in a fully deployed production system to recommend posting times for millions of users every day, and it is shown that users see a reaction gain of up to 17% on Facebook and 4% on Twitter when the recommended posting times are used.

Discovering Influence in Communication Networks Using Dynamic Graph Analysis

These are the first dynamic metrics for social networks which take into the account both global and local influence (pagerank and repliers), and can be applied to other communication networks as well.

Efficient influence maximization in social networks

Based on the results, it is believed that fine-tuned heuristics may provide truly scalable solutions to the influence maximization problem with satisfying influence spread and blazingly fast running time.

Measuring influence on Twitter

The research purpose of this paper is to determine a grounded approach for measuring social networking potential of individual Twitter users.

Online Topic-Aware Influence Maximization

This work proposes a faster topic-sample-based algorithm with e · (1 − 1/e) approximation ratio for any e ∈ (0, 1], which materializes the influence spread of some topic-distribution samples and utilizes the materialized information to avoid computing the actual influence of users with small influences.