RECORD
Debiasing Community Detection: The Importance of Lowly-Connected Nodes
Social and Information Networks · Submitted 19 Mar 2019
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experiments show that our approach outperforms the existing state-of-the-art in terms of F1 and Jaccard similarity scores while reducing the bias towards low-degree users.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Community detection is an important task in social network analysis, allowing us to identify and understand the communities within the social structures. However, many community detection approaches either fail to assign low degree (or lowly-connected) users to communities, or assign them to trivially small communities that prevent them from being included in analysis. In this work, we investigate how excluding these users can bias analysis results. We then introduce an approach that is more inclusive for lowly-connected users by incorporating them into larger groups. Experiments show that our approach outperforms the existing state-of-the-art in terms of F1 and Jaccard similarity scores while reducing the bias towards low-degree users.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Community detection is an important task in social network analysis, allowing us to identify and understand the communities within the social structures. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | However, many community detection approaches either fail to assign low degree (or lowly-connected) users to communities, or assign them to trivially small communities that prevent them from being included in analysis. | gap 0.61 | 0.06 | 0.06 | asserted 0.89 |
| s2 | In this work, we investigate how excluding these users can bias analysis results. | contribution 0.86 | 0.44 | 0.06 | unclear 0.77 |
| s3 | We then introduce an approach that is more inclusive for lowly-connected users by incorporating them into larger groups. | method 0.55 | 0.89 | 0.12 | asserted 0.99 |
| s4 | Experiments show that our approach outperforms the existing state-of-the-art in terms of F1 and Jaccard similarity scores while reducing the bias towards low-degree users. | result 1.00 | 0.96 | 0.77 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Community detection is an important task in social network analysis, allowing us to identify and understand the communities within the social structures. However, many community detection approaches either fail to assign low degree (or lowly-connected) users to communities, or assign them to trivially small communities that prevent them from being included in analysis. In this work, we investigate how excluding these users can bias analysis results. We then introduce an approach that is more inclusive for lowly-connected users by incorporating them into larger groups. Experiments show that our approach outperforms the existing state-of-the-art in terms of F1 and Jaccard similarity scores while reducing the bias towards low-degree users.
Human review
References
How the literature uses it
2 arXiv papers cite this in 4 sentences
Papers citing it · 1 sentence without a confident label
Cites it as support 1 paper
-
In [ref] authors show how this type of bias exists and is perpetuated by the existing community detection methods.
A Survey on Bias and Fairness in Machine Learning · Community Detection/Graph Embedding/Clustering · 0.98
Cites it as background 1 paper
-
From representation learning [ref] to graph embedding [ref] to community detection [ref] and clustering [ref] , researchers have studied biases in these areas and tried to address them by pointing out the observed problems and proposing new directions and ideas.
Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition · Related Work · 0.96
What it cites
Uses data or values from 1 paper
-
This dataset comes from [ref] in which we only utilized the seed users from the whole dataset which brought our dataset size down from more than million users to 10,074 users since we required pure ground truth labels that were obtained away from the network structure and label propagation.
Characterizing the 2016 Russian IRA Influence Campaign · U.S. Presidential Election · 1.00
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.