Kajwan Ziaoddini

Kajwan Ziaoddini

This paper examines how musical symbolism is produced and circulated in online communities by combining content-based music analysis with a lightweight network perspective on lyrics. Using a curated corpus of 275 chart-topping songs enriched with audio descriptors (energy, danceability, loudness, liveness, valence, acousticness, speechiness, popularity) and full lyric transcripts, we build a reproducible pipeline that (i) quantifies temporal trends in sonic attributes, (ii) models lexical salience and co-occurrence, and (iii) profiles mood by genre. We find a decade-long decline in energy (79 -> 58) alongside a rise in danceability (59 -> 73); valence peaks in 2013 (63) and dips in 2014-2016 (42) before partially recovering. Correlation analysis shows strong coupling of energy with loudness (r = 0.74) and negative associations for acousticness with both energy (r = -0.54) and loudness (r = -0.51); danceability is largely orthogonal to other features (|r| < 0.20). Lyric tokenization (>114k tokens) reveals a pronoun-centric lexicon "I/you/me/my" and a dense co-occurrence structure in which interpersonal address anchors mainstream narratives. Mood differs systematically by style: R&B exhibits the highest mean valence (96), followed by K-Pop/Pop (77) and Indie/Pop (70), whereas Latin/Reggaeton is lower (37) despite high danceability. Read through a subcultural identity lens, these patterns suggest the mainstreaming of previously peripheral codes and a commercial preference for relaxed yet rhythmically engaging productions that sustain collective participation without maximal intensity. Methodologically, we contribute an integrated MIR-plus-network workflow spanning summary statistics, correlation structure, lexical co-occurrence matrices, and genre-wise mood profiling that is robust to modality sparsity and suitable for socially aware recommendation or community-level diffusion studies.

Kajwan Ziaoddini

This study presents a novel Multi-Modal Graph Neural Network (MM-GNN) framework for socially aware music recommendation, designed to enhance personalization and foster community-based engagement. The proposed model introduces a fusion-free deep mutual learning strategy that aligns modality-specific representations from lyrics, audio, and visual data while maintaining robustness against missing modalities. A heterogeneous graph structure is constructed to capture both user-song interactions and user-user social relationships, enabling the integration of individual preferences with social influence. Furthermore, emotion-aware embeddings derived from acoustic and textual signals contribute to emotionally aligned recommendations. Experimental evaluations on benchmark datasets demonstrate that MM-GNN significantly outperforms existing state-of-the-art methods across various performance metrics. Ablation studies further validate the critical impact of each model component, confirming the effectiveness of the framework in delivering accurate and socially contextualized music recommendations.