Aspect-Based Sentiment Analysis for Future Tourism Experiences: A BERT-MoE Framework for Persian User Reviews

• URL: http://arxiv.org/abs/2602.12778v1
• Date: Fri, 13 Feb 2026 10:01:33 GMT
• Title: Aspect-Based Sentiment Analysis for Future Tourism Experiences: A BERT-MoE Framework for Persian User Reviews
• Abstract summary: This study advances aspect-based sentiment analysis (ABSA) for Persian-language user reviews in the tourism domain.<n>We propose a hybrid BERT-based model with Top-K routing and auxiliary losses to mitigate routing collapse and improve efficiency.<n>The proposed model achieves a weighted F1-score of 90.6% for ABSA, outperforming baseline BERT (89.25%) and a standard hybrid approach (85.7%)
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This study advances aspect-based sentiment analysis (ABSA) for Persian-language user reviews in the tourism domain, addressing challenges of low-resource languages. We propose a hybrid BERT-based model with Top-K routing and auxiliary losses to mitigate routing collapse and improve efficiency. The pipeline includes: (1) overall sentiment classification using BERT on 9,558 labeled reviews, (2) multi-label aspect extraction for six tourism-related aspects (host, price, location, amenities, cleanliness, connectivity), and (3) integrated ABSA with dynamic routing. The dataset consists of 58,473 preprocessed reviews from the Iranian accommodation platform Jabama, manually annotated for aspects and sentiments. The proposed model achieves a weighted F1-score of 90.6% for ABSA, outperforming baseline BERT (89.25%) and a standard hybrid approach (85.7%). Key efficiency gains include a 39% reduction in GPU power consumption compared to dense BERT, supporting sustainable AI deployment in alignment with UN SDGs 9 and 12. Analysis reveals high mention rates for cleanliness and amenities as critical aspects. This is the first ABSA study focused on Persian tourism reviews, and we release the annotated dataset to facilitate future multilingual NLP research in tourism.

Related papers

• SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA) [86.42477627274019]
  We present the SemEval-2026 shared task on Dimensional Aspect-Based Sentiment Analysis (DimABSA)<n>DimABSA improves traditional ABSA by modeling sentiment along valence-arousal (VA) dimensions rather than using categorical polarity labels.<n>To extend ABSA beyond consumer reviews to public-issue discourse, we introduce an additional task, Dimensional Stance Analysis (DimStance)<n>DimStance treats stance targets as aspects and reformulates stance detection as regression in the VA space.
  arXiv  Detail & Related papers  (2026-04-08T13:15:48Z)
• DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis [57.70022214686838]
  DimABSA is the first multilingual, dimensional ABSA resource annotated with both traditional ABSA elements and VA scores.<n>This resource contains 76,958 aspect instances across 42,590 sentences, spanning six languages and four domains.
  arXiv  Detail & Related papers  (2026-01-30T14:30:35Z)
• Tourism Question Answer System in Indian Language using Domain-Adapted Foundation Models [0.6524460254566904]
  This article presents the first comprehensive study on designing a baseline extractive question-answering (QA) system for the Hindi tourism domain.<n>It targets ten tourism-centric variants-Ganga Aarti, Cruise, Food Court, Public Toilet, Kund, Museum, General, Ashram, Temple and Travel.<n>We propose a framework leveraging foundation models-BERT and RoBERTa, fine-tuned using Supervised Fine-Tuning (SFT) and Low-Rank Adaptation (LoRA) to optimize parameter efficiency and task performance.
  arXiv  Detail & Related papers  (2025-11-28T14:44:16Z)
• RefineBench: Evaluating Refinement Capability of Language Models via Checklists [71.02281792867531]
  We evaluate two refinement modes: guided refinement and self-refinement.<n>In guided refinement, both proprietary LMs and large open-weight LMs can leverage targeted feedback to refine responses to near-perfect levels within five turns.<n>These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses.
  arXiv  Detail & Related papers  (2025-11-27T07:20:52Z)
• ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge [40.49917730563565]
  ESGenius is a comprehensive benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in Environmental, Social, and Governance (ESG)<n> ESGenius comprises two key components: (i) ESGenius-QA, a collection of 1,136 Multiple-Choice Questions (MCQs) generated by LLMs and rigorously validated by domain experts, covering a broad range of ESG pillars and sustainability topics; and (ii) ESGenius-Corpus, a meticulously curated repository of 231 foundational frameworks, standards, reports, and recommendation documents from 7 authoritative sources.
  arXiv  Detail & Related papers  (2025-06-02T13:19:09Z)
• Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval [49.1574468325115]
  We introduce Amharic-specific dense retrieval models based on pre-trained Amharic BERT and RoBERTa backbones.<n>Our proposed RoBERTa-Base-Amharic-Embed model (110M parameters) achieves a 17.6% relative improvement in MRR@10.<n>More compact variants, such as RoBERTa-Medium-Amharic-Embed (42M) remain competitive while being over 13x smaller.
  arXiv  Detail & Related papers  (2025-05-25T23:06:20Z)
• Enhancing Aspect-based Sentiment Analysis with ParsBERT in Persian Language [0.0]
  This paper aims to amplify the efficiency of language models tailored to the Persian language.<n>The study centers on sentiment analysis of user opinions extracted from the Persian website 'Digikala'
  arXiv  Detail & Related papers  (2025-02-03T06:25:06Z)
• Enhancing Aspect-based Sentiment Analysis in Tourism Using Large Language Models and Positional Information [14.871979025512669]
  This paper proposes an aspect-based sentiment analysis model, ACOS_LLM, for Aspect-Category--Sentiment Quadruple Extraction (ACOSQE) The model comprises two key stages: auxiliary knowledge generation and ACOSQE. Results demonstrate the model's superior performance, with an F1 improvement of 7.49% compared to other models on the tourism dataset.
  arXiv  Detail & Related papers  (2024-09-23T13:19:17Z)
• InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis [58.188050006989144]
  InstructABSA is an instruction learning paradigm for Aspect-Based Sentiment Analysis (ABSA) subtasks. Our method introduces positive, negative, and neutral examples to each training sample, and instruction tune the model (Tk-Instruct) for ABSA subtasks, yielding significant performance improvements.
  arXiv  Detail & Related papers  (2023-02-16T23:29:22Z)
• Exploiting BERT to improve aspect-based sentiment analysis performance on Persian language [0.0]
  This research shows the potential of using pre-trained BERT model and taking advantage of using sentence-pair input on an ABSA task. The results indicate that employing Pars-BERT pre-trained model along with natural language inference auxiliary sentence (NLI-M) could boost the ABSA task accuracy up to 91%.
  arXiv  Detail & Related papers  (2020-12-02T16:47:20Z)
• BAN-ABSA: An Aspect-Based Sentiment Analysis dataset for Bengali and it's baseline evaluation [0.8793721044482612]
  We present a manually annotated Bengali dataset of high quality, BAN-ABSA, which is annotated with aspect and its associated sentiment by 3 native Bengali speakers. The dataset consists of 2,619 positive, 4,721 negative and 1,669 neutral data samples from 9,009 unique comments gathered from some famous Bengali news portals.
  arXiv  Detail & Related papers  (2020-12-01T06:09:44Z)
• Understanding Pre-trained BERT for Aspect-based Sentiment Analysis [71.40586258509394]
  This paper analyzes the pre-trained hidden representations learned from reviews on BERT for tasks in aspect-based sentiment analysis (ABSA) It is not clear how the general proxy task of (masked) language model trained on unlabeled corpus without annotations of aspects or opinions can provide important features for downstream tasks in ABSA.
  arXiv  Detail & Related papers  (2020-10-31T02:21:43Z)
• Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis [71.40390724765903]
  Aspect-based sentiment analysis (ABSA) aims to predict the sentiment towards a specific aspect in the text. Existing ABSA test sets cannot be used to probe whether a model can distinguish the sentiment of the target aspect from the non-target aspects. We generate new examples to disentangle the confounding sentiments of the non-target aspects from the target aspect's sentiment.
  arXiv  Detail & Related papers  (2020-09-16T22:38:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.