Surreal illustration of interconnected nodes forming a brain, symbolizing online creativity and big data analysis.

Unlocking Online Creativity: How Big Data is Reshaping Social Networks

Author's portrait.
Kai Mendoza in Tech & Innovation September 2025 • 5 min read.

"Discover how innovative models analyzing big data can identify trends, predict user behavior, and foster creativity in the digital world."


In today's digital age, understanding human creativity is more vital than ever. Social networks and online platforms have revolutionized information exchange, creating unprecedented opportunities for interaction. The surge in big data analytics enables us to process event chains in real-time, offering profound insights into user behavior. This capability presents a unique challenge: how to study and optimize human engagement in an environment defined by continuous online access and an overwhelming influx of information.

One particularly promising yet underexplored area lies in modeling and comprehending the principles of online creativity. The posts and comments that users share on social networks form dynamic event chains, heavily influenced by both informational context and individual interests. Original ideas and opinions evolve from existing knowledge, sparking new discussions. While this process is generally self-organized, it can be guided by informational influence, whether positive (motivational stories, innovations) or negative (“fake news,” social deviations).

New research introduces a novel model of online creativity, specifically designed for online behavior analysis. This model aims to identify negative informational influences and promote positive engagement, marking a significant step forward in understanding and harnessing the power of online interactions.

The Online Creativity Model: A Deep Dive

Surreal illustration of interconnected nodes forming a brain, symbolizing online creativity and big data analysis.

The proposed model centers on a set of key concepts for each Internet user: log, focus, context, and overlay context. These elements work together to approximate and understand user behavior within online environments. The user community is represented by individual users (ui), where i ranges from 1 to Nu, the total number of users. These users share various types of content—posts, comments, messages, photos, videos, audio—represented by informational objects (pj), where j ranges from 1 to Nw, the total number of informational objects.

Social media can be described as an event chain, represented by the equation: Bij = (Ui, Pj, tij). Here, Bij denotes the interaction between user i and object j at time tij. This history of social media processing is traditionally presented as a log of object processing events, characterized by the combination of user, focus, and time. Each event is defined as: li,j,k = li,j,k (Pk, (Ui, fi,k, tij,k)) = {0,1}, where fi,k represents the user’s current interest, described by a tag cloud. The tag cloud is expressed as: fi,k = {(τη, wn,k)i,k}, where τη is a tag (keyword) with weight wn,k.

Key components of the model include:
  • Log: Records user interactions and activities.
  • Focus: Represents the user's current interests and attention.
  • Context: Reflects the user's knowledge base and perception.
  • Overlay Context: Additional information designed to modify focus and attract interest.
The model also accounts for changes in user focus, which represent the evolution of a user's interests. User behavior is determined by a combination of concurrent interests, each reflected in corresponding focus changes. Context also plays a crucial role, acting as a knowledge base that shapes a user's perception. This context can be described using ontologies in the form of semantic networks that evolve over time as users learn and forget information. These changes are formalized as a chain of contexts: Ci,m = {(Tl, wl,m)i,m}. Context changes correlate with modifications in user focus. To ensure positive perception, the focus cannot be entirely new; yet, it must differ enough from the existing context to spark interest. The correlation between context and focus changes is represented as events: ei,j,m = li,j,m (Pk, (Ui, Ci,m, ti,j,m)) = {0,1}.

The Future of Online Creativity

The research demonstrates that this model of online creativity can be effectively used for analyzing online behavior, identifying negative informational influences, and fostering positive engagement. By understanding and applying these principles, we can create more dynamic, creative, and beneficial online experiences for everyone.

About this Article -

This article was crafted using a human-AI hybrid and collaborative approach. AI assisted our team with initial drafting, research insights, identifying key questions, and image generation. Our human editors guided topic selection, defined the angle, structured the content, ensured factual accuracy and relevance, refined the tone, and conducted thorough editing to deliver helpful, high-quality information.See our About page for more information.

This article is based on research published under:

DOI-LINK: 10.1007/978-3-030-01174-1_25, Alternate LINK

Title: Online Creativity Modeling And Analysis Based On Big Data Of Social Networks

Journal: Advances in Intelligent Systems and Computing

Publisher: Springer International Publishing

Authors: Anton Ivaschenko, Anastasia Khorina, Pavel Sitnikov

Published: 2018-11-02

Everything You Need To Know

1

How does the online creativity model approximate user behavior, and what are its key components?

The model uses "log" to record user interactions, "focus" to represent current interests (using a tag cloud of keywords and weights), "context" as a knowledge base shaping user perception (represented by semantic networks or ontologies), and "overlay context" to modify focus and attract interest. The interplay of these elements enables the model to approximate user behavior within online environments.

2

How does the model represent social media interactions as an event chain, and what do the components of this representation signify?

The model represents social media interactions as an "event chain", denoted by Bij = (Ui, Pj, tij). Here, Bij signifies the interaction between user i and object j at time tij, where Ui represents the user, Pj represents the informational object (post, comment, etc.), and tij represents the time of interaction. This formulation captures the temporal dynamics of user-object interactions within the social network.

3

How are context and focus changes represented in this online creativity model?

The model defines context changes as a chain of contexts: Ci,m = {(Tl, wl,m)i,m}, where Tl represents a tag (keyword) within the context and wl,m its weight. Focus changes are reflected in a user's current interests, described by a tag cloud: fi,k = {(τη, wn,k)i,k}, where τη is a tag (keyword) with weight wn,k. The model correlates the context and focus changes as events ei,j,m = li,j,m (Pk, (Ui, Ci,m, ti,j,m)) = {0,1}.

4

How might the online creativity model be used to enhance user engagement and mitigate negative influences online, and what ethical considerations are relevant?

The online creativity model could assist in identifying negative informational influences, such as misinformation, and promote positive engagement within online platforms. By analyzing user interactions, the model can detect patterns associated with the spread of harmful content and, conversely, amplify the reach of beneficial information, creating a more constructive online environment. However, the model doesn't explicitly address the ethical considerations of manipulating user focus.

5

How does the concept of 'focus' utilize tag clouds, and what advancements in natural language processing could enhance its representation of user interests?

The model uses “focus” to represent a user's current interests through a "tag cloud" (fi,k), consisting of keywords (τη) with associated weights (wn,k). This tag cloud evolves over time as the user interacts with different informational objects. The model could use natural language processing to refine tag extraction and sentiment analysis to better represent the emotional tone of the tags.

Newsletter Subscribe

Subscribe to get the latest articles and insights directly in your inbox.