AUTHOR=Ni Yingying , Ni Wei TITLE=A multi-label text sentiment analysis model based on sentiment correlation modeling JOURNAL=Frontiers in Psychology VOLUME=Volume 15 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2024.1490796 DOI=10.3389/fpsyg.2024.1490796 ISSN=1664-1078 ABSTRACT=This paper proposes ECO-SAM, a sentiment correlation modeling-based multilabel sentiment analysis model.[Methods] ECO-SAM utilizes the pretrained BERT encoder to obtain semantic embeddings of input texts, then leverages the self-attention mechanism to model the semantic correlation between emotions. Finally, ECO-SAM utilizes a text-emotion matching neural network to make sentiment analysis for input texts.[Results] Experiment results in public datasets demonstrate that compared to baseline models, ECO-SAM obtains the precision score increasing by 13.33% at most, the recall score increasing by 3.69% at most, the F1 score increasing by 8.44% at most. Meanwhile, the modeled sentiment semantics are interpretable.[Limitations] The data modeled by ECO-SAM is limited to text modal, ignoring multimodal data that may enhance classification performance. The training data is not large scale, and there lack large-scale high-quality training data for fine-tuning sentiment analysis models.[Conclusions] ECO-SAM is capable for effectively modeling sentiment semantics and achieve excellent classification performance in many public sentiment analysis datasets.