Upload Data
Select K
View Results
File uploaded successfully

Data Preparation

Welcome! Please follow the steps below to upload your data (.xlsx) and specify essential parameters for movement analysis.

Upload Excel File

Choose a file or drag it here

Select Analysis Unit & Code

Analysis Unit: ?
An analysis unit is the actor or entity for which the movement is created. It can be an individual learner, a group, or a time segment.

Code: ?
A code is a label or category applied to portions of data (e.g., text, speech, or actions) that represent ideas, behaviors, or themes relevant to the analysis.

Enter Stanza Size ?
A stanza refers to a segment or unit of discourse within which co-occurrences of codes (representing ideas, concepts, or behaviors) are analyzed to examine their connections. Stanzas can be defined in various ways, such as a turn of talk in a conversation, a paragraph in written text, or a time window in collaborative tasks. Choosing an appropriate stanza size is critical and depends on the nature of the data, the research questions, and the theoretical framework guiding the study. Smaller stanzas, such as single utterances or sentences, capture fine-grained interactions but may lead to sparse networks, while larger stanzas, such as paragraphs or task phases, aggregate more connections but risk including unrelated ideas. The optimal stanza size balances granularity and interpretability, ensuring the connections analyzed are meaningful within the given context.

Stanza Clustering

In this step, a clustering analysis is performed to group stanzas with similar structures based on co-occurrences of codes within stanzas. The following procedures use the elbow method to determine the optimal number of clusters.

WCSS (Within-Cluster Sum of Squares)
Look for the point where the curve bends significantly

Generate Movement ?
The k value represents the number of clusters into which the data is partitioned. It defines how the algorithm groups data points such that points within the same cluster are more similar to each other than to those in other clusters, based on a chosen distance metric (e.g., Euclidean distance). Choosing an appropriate k is crucial as it directly affects the quality and interpretability of the clustering results. One common method for determining k is the elbow method, which involves plotting the within-cluster sum of squares (WCSS)—a measure of how tightly data points are grouped within clusters—against different values of k. As k increases, WCSS generally decreases because more clusters lead to smaller, tighter groupings. The "elbow point" on the plot, where the rate of decrease in WCSS sharply diminishes, indicates the optimal k, balancing model complexity and explanatory power.