--- title: "MRS at SemEval-2025 Task 11 — Afshari 2025" description: "The paper addresses SemEval-2025 Task 11, Track A: multi-label emotion recognition in short English texts." authors: ["Milad Afshari", "Richard Frost", "Samantha Kissel", "Kristen Johnson"] year: 2025 venue: "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)" source: "https://aclanthology.org/2025.semeval-1.81/" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/papers/afshari-2025-mrs-semeval-2025-task-11/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/afshari-2025-mrs-semeval-2025-task-11/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2025](https://md.research.elamur.ai/free/papers/2025/page/2/) / MRS at SemEval-2025 Task 11: A Hybrid Approach for Bridging the Gap in Text-Based Emotion Detection # MRS at SemEval-2025 Task 11: A Hybrid Approach for Bridging the Gap in Text-Based Emotion Detection **Authors:** Milad Afshari, Richard Frost, Samantha Kissel, Kristen Johnson · **Year:** 2025 · **Venue:** Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2025.semeval-1.81/) · [PDF](https://aclanthology.org/2025.semeval-1.81.pdf) ## Summary The paper addresses SemEval-2025 Task 11, Track A: multi-label emotion recognition in short English texts. For each text, the task is to determine which of five emotions most people would perceive in the speaker's words: anger, fear, joy, sadness, or surprise. The authors propose RoEmo, a system that combines models of two types. The first, a discriminative model, is RoBERTa-large with a two-layer MLP on top. It solves a separate binary task for each emotion. The second, a generative model, is EmoT5 from the EmoLLMs family, which was previously tuned on affective instructions. It was further fine-tuned on the competition data in a text-to-text format with a dedicated prompt. The models' outputs are combined with a logical OR: an emotion is considered present if at least one of them detects it. This raises recall at the cost of a slight drop in precision, but overall macro-F1 improves. On the test set, the ensemble outperformed both individual models and placed among the top systems in the competition. The result shows that even a very simple combination of models from different paradigms yields a noticeable gain on a subjective and ambiguous task. ## Key points - Track A data (English only): 2,768 training, 116 dev, and 2,767 test examples. Annotation was done via Amazon Mechanical Turk, and text length ranges from 4 to 121 tokens. Besides the five emotions, there are neutral examples, and a single text may contain several emotions at once. - Both models were trained for 15 epochs with the AdamW optimizer (learning rate 2×10⁻⁵) on a single NVIDIA RTX A6000. - Test: RoEmo achieves a macro-F1 of 0.7659, compared with 0.7552 for RoBERTa-large and 0.747 for EmoT5; RoEmo's micro-F1 is 0.7913. - Dev: macro-F1 is 0.7821 for RoEmo, 0.7514 for RoBERTa-large, and 0.7625 for EmoT5. - On the test set, texts with anger are the hardest (F1 ≈ 0.67) and texts with fear the easiest (≈ 0.86). The ensemble improved results for all emotions except joy, where RoEmo slightly underperformed both models. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{afshari2025mrs, title = {{MRS at SemEval-2025 Task 11: A Hybrid Approach for Bridging the Gap in Text-Based Emotion Detection}}, author = {Afshari, Milad and Frost, Richard and Kissel, Samantha and Johnson, Kristen}, booktitle = {Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)}, year = {2025}, url = {https://aclanthology.org/2025.semeval-1.81/} } ``` - [← previous MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators](https://md.research.elamur.ai/free/papers/lu-2025-mqm-ape-high-quality-error/) - [next → MultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation](https://md.research.elamur.ai/free/papers/sentsova-2025-multicopie-multilingual-corpus-potentially-idiomatic/) - [↑ back to papers of 2025](https://md.research.elamur.ai/free/papers/2025/page/2/) ## References 1 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Abdullah Al Maruf, Fahima Khanam, Md Mahmudul Haque, Zakaria Masud Jiyad, Firoj Mridha, and Ze-yar Aung. 2024. Challenges and opportunities of text-based emotion detection: A survey. IEEE Access. *Table 4: Evaluation scores on the Test dataset* tive approach for multi-label emotion classification. \#… [find](https://scholar.google.com/scholar?q=Abdullah+Al+Maruf%2C+Fahima+Khanam%2C+Md+Mahmudul+Haque%2C+Zakaria+Masud+Jiyad%2C+Firoj+Mridha%2C+and+Ze%2Dyar+Aung%2E+2024%2E+Challenges+and+opportunities+of+text%2Dbased+emotion+detection%3A+A+survey%2E+IEEE+Access%2E+%2ATab)