Assessing the Performance of AI Models in Misinformation Detection Using Predefined Social Noise Constructs

Manar Alsaid

cs.LGOct 12, 2026

Assessing the Performance of AI Models in Misinformation Detection Using Predefined Social Noise Constructs

Authors: Manar Alsaid

Organizations: East Texas A&M University, Department of Computer Science and Information Systems, Commerce, Texas, USA

Abstract

Social media platforms generate vast volumes of user-generated content that often obscure meaningful discourse, a phenomenon conceptualized as social noise. While existing misinformation detection methods primarily focus on factual verification, they largely overlook the role of social noise in amplifying misinformation. This study assesses the performance of six text-based models and a graph neural network (GNN) in mitigating the effects of misinformation using predefined social noise constructs. The dataset consists of 500,000 tweets collected from the X platform using the Ukraine hashtag during the Russia-Ukraine conflict from March 2024 to March 2025. Advanced machine learning models achieve strong performance, with accuracies ranging from 79.94% to 97.17%. RoBERTa demonstrates the highest performance, with an accuracy of 97.17%, Cohen's kappa of 0.9660, MCC of 0.9660, and AUC of 0.9977. The GNN achieves an accuracy of 64.52% and an AUC of 0.899, demonstrating performance above random-chance classification by exploiting the relational structure between tweets. All text-based models achieve kappa values greater than 0.75, indicating substantial overall agreement. Explainable AI analysis using LIME reveals that 89.6% of predictive weight is attributed to contextual features rather than isolated keywords. The findings highlight that integrating social noise into AI pipelines enhances misinformation detection and supports more effective mitigation strategies in large-scale social media environments.

Figures & tables

Model	Image	Relationship	Conflict	Cultural	Affiliation	Norms
	Curation	Management	Engagement	Agency	& Politics	& Beliefs
RoBERTa (Pre-trained Transformer)	✓	✓	✓	✓	✓	✓
BiLSTM + Multi-head Self-Attention	✓	✓	✓	✓	✓	✓
Multi-scale Residual CNN + SE Attention	✓	✓	✓	✓	✓	✓
XGBoost	✓	✓	✓	✓	✓	✓
Random Forest	✓	✓	✓	✓	✓	✓

Table 1. Six Models Evaluated Across Six Social Noise Constructs

Model	Configuration	Parameters
GCN	Symmetric spectral normalization with a residual skip connection from the input layer to the first hidden layer. Hidden dimension: 256.	1,608,199
GAT	Two-layer attention mechanism. The first two layers used eight parallel attention heads with concatenated outputs to maintain a hidden size of 256; the output layer used a single head.	839,445
GraphSAGE	Mean-based inductive neighborhood aggregation, updating each node representation by concatenating its embedding with the mean of its neighbors’ embeddings.	1,675,271
GIN	Weisfeiler–Leman expressive aggregation using a two-layer MLP, 256 to 256 with ReLU, applied to the sum of each node’s own representation and its neighbors’ representations.	1,035,783

Table 2. Graph Neural Network Architectures Used in the Propagation Analysis

Metric	AP	CE	CA	IC	NB	RM	Macro Avg.
Precision	0.9715	0.9815	0.9591	0.9591	0.9797	0.9798	0.9718
Recall	0.9650	0.9733	0.9767	0.9767	0.9667	0.9717	0.9717
F1-score	0.9682	0.9774	0.9678	0.9678	0.9732	0.9757	0.9717
Cohen’s $\kappa$	0.9672	0.9698	0.9598	0.9589	0.9668	0.9710	0.9667
MCC	0.9665	0.9670	0.9578	0.9567	0.9670	0.9716	0.9666

Table 3. RoBERTa classification results for each social noise construct. Overall accuracy = 97.17%.

Metric	AP	CE	CA	IC	NB	RM	Macro Avg.
Precision	0.9396	0.9796	0.9614	0.9672	0.9382	0.9523	0.9564
Recall	0.9600	0.9600	0.9550	0.9350	0.9617	0.9650	0.9561
F1-score	0.9497	0.9697	0.9582	0.9508	0.9498	0.9586	0.9561
Cohen’s $\kappa$	0.9487	0.9560	0.9498	0.9298	0.9289	0.9686	0.9476
MCC	0.9454	0.9458	0.9431	0.9289	0.9279	0.9677	0.9476

Table 4. XGBoost classification results for each social-noise constructs.

Metric	AP	CE	CA	IC	NB	RM	Macro Avg.
Precision	0.9210	0.9085	0.8620	0.8947	0.8195	0.8967	0.8837
Recall	0.8950	0.9183	0.8850	0.8350	0.8700	0.9100	0.8856
F1-score	0.9078	0.9134	0.8733	0.8638	0.8440	0.9033	0.8843
Cohen’s $\kappa$	0.8810	0.9001	0.8599	0.8089	0.8190	0.8871	0.8649
MCC	0.8800	0.9101	0.8589	0.8000	0.8180	0.8710	0.8649

Table 5. RoBERTa classification results without keywords for each social-noise constructs.

Metric	AP	CE	CA	IC	NB	RM	Macro Avg.
Precision	0.9435	0.8948	0.9043	0.9457	0.6805	0.8677	0.8727
Recall	0.9183	0.8367	0.8817	0.9000	0.8733	0.7650	0.8625
F1-score	0.9307	0.8648	0.8928	0.9223	0.7650	0.8131	0.8648
Cohen’s $\kappa$	0.9011	0.8267	0.8786	0.8981	0.6948	0.7278	0.8350
MCC	0.9001	0.8261	0.8643	0.8991	0.6989	0.7274	0.8350

Table 6. XGBoost classification results without keywords for each social-noise constructs.

Model	Accuracy (%)	Cohen’s $\kappa$	MCC	F1-score	Log Loss
RoBERTa-base	97.17	0.966	0.966	0.9717	0.1304
BiLSTM+Attn	96.94	0.963	0.963	0.9694	0.1270
CNN+SE	96.69	0.960	0.960	0.9670	0.1280
XGBoost	95.61	0.947	0.947	0.9561	0.1370
Random Forest	91.69	0.900	0.901	0.9169	0.3070
AdaBoost	79.94	0.759	0.761	0.8008	0.6000

Table 7. Text classification model performance comparison with keywords across the six social noise constructs.

Model	Acc. w/o KW	Acc. Drop	F1 w/o KW	F1 Drop	$\kappa$ w/o KW	$\kappa$ Drop	Retained
RoBERTa	88.69%	$-8.48$	0.8870	$-0.0847$	0.864	$-0.102$	91.3%
BiLSTM+Attn	16.67%	$-80.27$	0.0476	$-0.9218$	0.000	$-0.963$	17.2%
CNN+SE	87.06%	$-9.63$	0.8735	$-0.0935$	0.845	$-0.115$	90.0%
XGBoost	86.25%	$-9.36$	0.8648	$-0.0913$	0.835	$-0.112$	90.2%
Random Forest	83.83%	$-7.86$	0.8415	$-0.0754$	0.806	$-0.094$	91.4%
AdaBoost	68.64%	$-11.30$	0.7061	$-0.0947$	0.624	$-0.135$	85.9%

Table 8. AI classification model performance comparison without keywords across the 6 social-noise constructs.

Figure 1. social noise construct classification models comparison with keywords versus without keywords. Performance comparison of multiple classification models trained with and without keyword features, showing differences in accuracy and robustness.

Deep Learning Models
Model	AP	CE	CA	IC	NB	RM	Avg.
RoBERTa	0.0	1.7	21.6	16.4	60.4	1.6	16.9
BiLSTM+Attn	6.7	20.0	1.2	2.1	45.6	19.3	15.8
CNN+SE	3.2	96.7	3.0	0.0	22.7	8.8	22.4
Machine Learning Models
XGBoost	0.9	18.0	0.0	0.0	34.4	9.1	10.4

Table 9. XAI with keywords: keyword feature reliance (%) across all ten models. Values indicate the percentage of each model’s prediction driven by labeling keywords.

Model	Acc. w/o KW	Acc. Drop (pp)	F1 w/o KW	F1 Drop	$\kappa$ w/o KW	Retained
Deep Learning Models
RoBERTa	88.69%	$-8.48$	0.8870	$-0.0847$	0.864	91.3%
BiLSTM+Attn	16.67%	$-80.27$	0.0476	$-0.9218$	0.000	17.2%
CNN+SE	87.06%	$-9.63$	0.8735	$-0.0935$	0.845	90.0%
Traditional Machine Learning Models
XGBoost	86.25%	$-9.36$	0.8648	$-0.0913$	0.835	90.2%

Table 10. Performance without keywords: classification results after removing all labeling keywords.

Figure 2. Average pairwise Jaccard similarity of top-15 LIME features across four models (RoBERTa, XGBoost, Random Forest, AdaBoost) for each social noise construct. Higher values indicate greater cross-model agreement on which features define a given construct. The dashed line marks the overall mean ( $J=0.458$ ). Bar chart showing average pairwise Jaccard similarity of top-15 LIME features across four models for each of the six social noise constructs. Affiliation and Politics have the highest overlap at 0.688, followed by Norms and Beliefs at 0.610, while Conflict Engagement has the lowest at 0.282.

Metric	GCN	GAT	GraphSAGE	GIN
Accuracy	0.3010	0.6362	0.3514	0.6452
Cohen’s $\kappa$	0.1844	0.5756	0.2433	0.5861
MCC	0.2219	0.5759	0.2819	0.5867
F1 Macro	0.1942	0.6377	0.2756	0.6471
F1 Weighted	0.1942	0.6377	0.2756	0.6471
Precision Macro	0.2756	0.6408	0.4188	0.6528

Table 11. Full Evaluation of the Four GNN Models on the Held-Out Test Set

Construct	GCN	GAT	GraphSAGE	GIN
Affiliation and Politics	0.0641	0.6319	0.2471	0.6431
Conflict Engagement	0.3958	0.6992	0.0000	0.6947
Cultural Agency	0.0000	0.6309	0.2286	0.6083
Image Curation	0.0000	0.6609	0.4114	0.6784
Norms and Beliefs	0.4972	0.6929	0.6441	0.6990
Relationship Management	0.0000	0.6271	0.0000	0.6618

Table 12. Per-Class F1 Scores Across the Seven Classification Categories

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Construct	Definition	All Keywords
Image Curation	Is the effort by a social media user, consciously or unconsciously, to craft their online identities	please, willing, identity, recommend, report, thank, determination, express, filter, glow up, online persona, blessed, appreciate, grateful, effort, try, connect, inspire, style, follow, vibe, share, careful, build, personalize, aesthetic, rebrand, curate, highlight, showcase, authentic, unfiltered, realme, selfie, transformation, glow, reinvent, portfolio, brand, influencer, goals, milestone, achievement, flex, posture, visibility, credibility, impression, perception, polished, reputation, narrative, self-promote, presence, lifestyle, snapshot, moment, debut, reveal, spotlight
Relationship Management	Refers to a user’s understanding of their roles and responsibilities within social institutions as well as the level of confidence in their personal beliefs	love, want, help, please, equivalent, humanity, stop, violence, awareness, defense, influence, mutual aid, absurdity, ordained, advising, trust, personal, values, support, system, role, follow, link, caretaker, share, build, bond, network, community, solidarity, ally, engage, connect, collaborate, partnership, unity, belong, inclusion, outreach, brotherhood, sisterhood, tribe, circle, uplift, empower, mentor, peer, kinship, loyalty, reciprocity, validate, affirm, acknowledge, compassion, empathy, check in, hold space, stand with, together, with you
Conflict Engagement	Is the level of social conflict with which a user is comfortable	report, stop, humiliation, mistreat, misconduct, controversial, discord, confront, stand, call out, cancel, criticism, drama, argue, debate, disagree, feud, end, stand by, challenge, exposed, push back, clash, trigger, offensive, toxic, harass, troll, bully, attack, block, mute, ban, dragged, ratio, receipts, problematic, accountability, blast, cancel culture, beef, clap back, shut down, respond, dispute, resist, counter, reject, silence, defend, expose, unfollow, clapback, petty
Cultural Agency	Is characterized by civic participation in social issues and is exhibited by individuals who believe in their own power to be heard and to shape culture and beliefs	radical, recommend, demand, justice, lives, matter, revolution, leadership, diversity, community, social, systemic, engagement, civic, raise, awareness, empowered, movement, voice, agency, disrupt, change, advocate, cultural, shift, representation, take, stand, allyship, protest, activism, mobilize, solidarity, march, petition, boycott, organize, grassroots, narrative, reclaim, decolonize, equity, liberation, amplify, platform, intersectionality, privilege, oppression, systemic change, reform, rally, coalition, impact, visibility, humanize, uplift, marginalized, speak up, movement building, social justice, power
Affiliation and Politics	Is characterized by loyalty to a political party, religion, or an organization. This could include people paid to carry out certain activities or advertise certain products.	Foxnews, sisracist, systemic, racism, supremacist, supremacy, racist, white, left, fascist, abiding, loyalist, influencer, vote, supporter, endorse, propaganda, party line, lobby, affiliated, news, report, campaign, black, right, MAGA, woke, liberal, conservative, leftist, right-wing, Democrat, Republican, partisan, polarized, deep state, mainstream media, fake news, conspiracy, agenda, endorsed, sponsored, bot, astroturfing, dark money, PAC, echo chamber, tribe, dogma, manifesto, ideology, regime, coup, fringe, extremist, radicalized, red pill, blue pill, disinformation, influence operation
Norms and Beliefs	Is characterized by deep beliefs, culture, ideology, religion, a cause etc.	change, culture, demand, justice, equity, inclusion, fight, racism, socialists, communists, anarchists, conservatives, extremists, religion, moral, values, cultural, identity, spiritual, practices, tradition, faith, doctrine, sacred, afterlife, scripture, nationalism, karma, virtue, ethics, principle, creed, conviction, righteousness, worldview, taboo, sin, blessed, prayer, amen, truth, awakening, salvation, prophet, divine, judgment, heresy, redemption, blasphemy, anti-woke, natural law, evolution, creationism, pro-life, pro-choice, freedom, sovereignty, anarchy, patriotism, censorship, heritage, purity, indoctrination

Appendix

Table 13. Social Noise Constructs definitions and sample keywords

Fake News Detection

Fake news detection identifies false or misleading claims by analyzing content, context, evidence, and how information spreads.

See all 85 papers

Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs
Apr 9, 2026Soveatin Kuntur, Maciej Krzywda, Anna Wróblewska +4Graph Neural Networks Fake News Detection
Warsaw University of Technology, plac Politechniki 1, 00-661 Warsaw, Poland · Corresponding author · AGH University of Krakow, Faculty of Physics and Applied Computer Science, Krakow, Poland +4
Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
May 19, 2026Bing Wang, Rui Miao, Ximing Li +6Fake News Detection LLM Fine-Tuning
College of Computer Science and Technology, Jilin University Changchun, China · Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, Jilin University · School of Artificial Intelligence, Jilin University Changchun, China +3
Detecting AI-Generated Content on Social Media with Multi-modal Language Models
Apr 21, 2026Chenyang Yang, Shen Yan, Yibo Yang +13Vision-Language Models AI-Generated Image Detection
Carnegie Mellon University · Meta

Apr 9, 2026J/K move · Enter open · S save

Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs

Soveatin Kuntur, Maciej Krzywda, Anna Wróblewska, Marcin Paprzycki+3

Warsaw University of Technology, plac Politechniki 1, 00-661 Warsaw, Poland · Corresponding author · AGH University of Krakow, Faculty of Physics and Applied Computer Science, Krakow, Poland+4

Graph Neural Networks Fake News Detection

Open paper AskPDF arXiv

The rapid spread of online misinformation has led to increasingly complex detection models, including large language models and hybrid architectures. However, their computational cost and deployment limitations raise concerns about practical applicability. In this work, we benchmark graph neural networks (GNNs) against non-graph-based machine learning methods under controlled and comparable conditions. We evaluate lightweight GNN architectures (GCN, GraphSAGE, GAT, ChebNet) against Logistic Regression, Support Vector Machines, and Multilayer Perceptrons across seven public datasets in English, Indonesian, and Polish. All models use identical TF-IDF features to isolate the impact of relational structure. Performance is measured using F1 score, with inference time reported to assess efficiency. GNNs consistently outperform non-graph baselines across all datasets. For example, GraphSAGE achieves 96.8% F1 on Kaggle and 91.9% on WELFake, compared to 73.2% and 66.8% for MLP, respectively. On COVID-19, GraphSAGE reaches 90.5% F1 vs. 74.9%, while ChebNet attains 79.1% vs. 66.4% on FakeNewsNet. These gains are achieved with comparable or lower inference times. Overall, the results show that classic GNNs remain effective and efficient, challenging the need for increasingly complex architectures in misinformation detection.

Abstract

Fake News Detection

Explore similar work

Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs

Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection

Detecting AI-Generated Content on Social Media with Multi-modal Language Models