{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:46Z","timestamp":1750309426407,"version":"3.41.0"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"12","license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2024,12,31]]},"abstract":"<jats:p>Sentiment analysis is a critical task for natural language processing. Much research has been done for high-resource languages such as English and Chinese. However, Tibetan is an extremely low resource language with less reference information. According to the practical demands, this article proposes RPEPL, a Tibetan sentiment analysis method based on relative position encoding and prompt learning. First, word information is introduced to syllable sequences by converting the directed acyclic lattice into a squashed structure. Second, a relative position encoding is used to encode the position information of syllables and words. Third, the association relations and semantic information of tokens are identified by leveraging the multi-attention. Finally, the sentiment category of the Tibetan sentence is obtained through a prompt learning framework. Experimental results demonstrate that RPEPL significantly outperforms the baseline methods on the TUSA dataset and TNEC (Tibetan News Event Comments) dataset. Additionally, traditional recurrent neural networks cannot perform large-scale parallel computation and convolutional neural networks have difficulty modeling long-distance dependencies in Tibetan text, both of which are resolved using RPEPL. Furthermore, the use of multi-attention not only enriches the association relations between syllables and words but also enhances the understanding of sentence semantic and syntactic structure information, and improves the performance of Tibetan sentiment analysis.<\/jats:p>","DOI":"10.1145\/3698575","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T11:21:40Z","timestamp":1728472900000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["RPEPL: Tibetan Sentiment Analysis Based on Relative Position Encoding and Prompt Learning"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1276-1504","authenticated-orcid":false,"given":"Chunwei","family":"Kong","sequence":"first","affiliation":[{"name":"School of Computer Science, Qinghai Normal University, Xining, China and Beijing Key Laboratory of Internet Culture and Digital Dissemination Research, Beijing Information Science and Technology University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1674-6395","authenticated-orcid":false,"given":"Xueqiang","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Computer Science, Qinghai Normal University, Xining, China and Beijing Key Laboratory of Internet Culture and Digital Dissemination Research, Beijing Information Science and Technology University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9620-511X","authenticated-orcid":false,"given":"Le","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Internet Culture and Digital Dissemination Research, Beijing Information Science and Technology University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0957-1603","authenticated-orcid":false,"given":"Haixing","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Qinghai Normal University, Xining, China, The State Key Laboratory of Tibetan Intelligent Information Processing and Application, Qinghai Normal University, Xining, China, and Key Laboratory of Tibetan Information Processing, Ministry of Education, Qinghai Normal University, Xining, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6056-7401","authenticated-orcid":false,"given":"Zangtai","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Qinghai Normal University, Xining, China, The State Key Laboratory of Tibetan Intelligent Information Processing and Application, Qinghai Normal University, Xining, China, and Key Laboratory of Tibetan Information Processing, Ministry of Education, Qinghai Normal University, Xining, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5706-3957","authenticated-orcid":false,"given":"Yuzhong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Qinghai Normal University, Xining, China, The State Key Laboratory of Tibetan Intelligent Information Processing and Application, Qinghai Normal University, Xining, China, and Key Laboratory of Tibetan Information Processing, Ministry of Education, Qinghai Normal University, Xining, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"issue":"9","key":"e_1_3_3_2_2","first-page":"2783","article-title":"Sentiment classification method based on multi-channel features and self-attention","volume":"32","author":"Li Weijiang","year":"2021","unstructured":"Weijiang Li, Fang Qi, and Zhengtao Yu. 2021. Sentiment classification method based on multi-channel features and self-attention. Journal of Software 32, 9 (2021), 2783\u20132800.","journal-title":"Journal of Software"},{"issue":"4","key":"e_1_3_3_3_2","first-page":"737","article-title":"Aspect-based sentiment analysis model based on multi-dependency graph and knowledge fusion","volume":"38","author":"He Yongxi","year":"2024","unstructured":"Yongxi He, Hu Han, and Bo Kong. 2024. Aspect-based sentiment analysis model based on multi-dependency graph and knowledge fusion. Journal of Zhejiang University (Engineering Science) 38, 4 (2024), 737\u2013747.","journal-title":"Journal of Zhejiang University (Engineering Science)"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3603168"},{"issue":"2","key":"e_1_3_3_5_2","first-page":"71","article-title":"Sentiment analysis of Tibetan short texts based on graphical neural networks and pre-training models","volume":"37","author":"Zhu Yulei","year":"2023","unstructured":"Yulei Zhu, Kazhuo Deji, Nuo Qun, and Tashi Nyima. 2023. Sentiment analysis of Tibetan short texts based on graphical neural networks and pre-training models. Journal of Chinese Information Processing 37, 2 (2023), 71\u201379.","journal-title":"Journal of Chinese Information Processing"},{"issue":"2","key":"e_1_3_3_6_2","first-page":"80","article-title":"Tibetan text sentiment classification combining syllables and words","volume":"37","author":"Meng Xianghe","year":"2023","unstructured":"Xianghe Meng and Hongzhi Yu. 2023. Tibetan text sentiment classification combining syllables and words. Journal of Chinese Information Processing 37, 2 (2023), 80\u201386.","journal-title":"Journal of Chinese Information Processing"},{"key":"e_1_3_3_7_2","first-page":"5755","article-title":"Unified structure generation for universal information extraction","author":"Lu Yaojie","year":"2022","unstructured":"Yaojie Lu, Qing Liu, Dai Dai, Xinyan Xiao, Hongyu Lin, Xianpei Han, Le Sun, and Hua Wu. 2022. Unified structure generation for universal information extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 5755\u20135772.","journal-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics"},{"key":"e_1_3_3_8_2","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Mingwei Chang, Kento Lee, and Kristina Toutanova. 2019. BERT: Pretraining of deep bidirectional transformers for language understanding. In Proceeding of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171\u20134183.","journal-title":"Proceeding of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"issue":"1","key":"e_1_3_3_9_2","first-page":"106","article-title":"Design of a sentiment classification system for Tibetan texts","volume":"40","author":"Li Haizhou","year":"2011","unstructured":"Haizhou Li and Hongzhi Yu. 2011. Design of a sentiment classification system for Tibetan texts. Scientific & Technical Information of Gansu 40, 1 (2011), 106\u2013107.","journal-title":"Scientific & Technical Information of Gansu"},{"key":"e_1_3_3_10_2","volume-title":"Research on Tibetan Sentence Orientation Analysis. Master's Thesis","author":"Du Xuefeng","year":"2015","unstructured":"Xuefeng Du. 2015. Research on Tibetan Sentence Orientation Analysis. Master's Thesis. Minzu University of China, Beijing, China."},{"issue":"3","key":"e_1_3_3_11_2","first-page":"682","article-title":"Research on sentiment analysis of Tibetan microblogs based on emotional dictionary","volume":"33","author":"Zhang Jun","year":"2016","unstructured":"Jun Zhang and Yingxing Li. 2016. Research on sentiment analysis of Tibetan microblogs based on emotional dictionary. Silicon Valley 33, 3 (2016), 682\u2013685.","journal-title":"Silicon Valley"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.14257\/ijmue.2016.11.9.38"},{"issue":"11","key":"e_1_3_3_13_2","first-page":"218","article-title":"Research on construction of Tibetan emotional dictionary and emotional computing of microblog","volume":"28","author":"Sun Benwang","year":"2018","unstructured":"Benwang Sun and Fang Tian. 2018. Research on construction of Tibetan emotional dictionary and emotional computing of microblog. Computer Technology and Development 28, 11 (2018), 218\u2013222.","journal-title":"Computer Technology and Development"},{"issue":"2","key":"e_1_3_3_14_2","first-page":"75","article-title":"Tibetan sentence sentiment classification based on emotion dictionary","volume":"32","author":"Yan Xiaodong","year":"2018","unstructured":"Xiaodong Yan and Tao Huang. 2018. Tibetan sentence sentiment classification based on emotion dictionary. Journal of Chinese Information Processing 32, 2 (2018), 75\u201380.","journal-title":"Journal of Chinese Information Processing"},{"issue":"3","key":"e_1_3_3_15_2","first-page":"682","article-title":"Emotional classification method of Tibetan micro-blog based on semantic space","volume":"33","author":"Yuan Bin","year":"2016","unstructured":"Bin Yuan, Tao Jiang, and Hongzhi Yu. 2016. Emotional classification method of Tibetan micro-blog based on semantic space. Application Research of Computers 33, 3 (2016), 682\u2013685.","journal-title":"Application Research of Computers"},{"issue":"3","key":"e_1_3_3_16_2","first-page":"163","article-title":"Multi-feature based sentiment analysis of Tibetan microblogs","volume":"31","author":"Jiang Tao","year":"2017","unstructured":"Tao Jiang, Bin Yuan, Hongzhi Yu, and Yangji Jia. 2017. Multi-feature based sentiment analysis of Tibetan microblogs. Journal of Chinese Information Processing 31, 3 (2017), 163\u2013169.","journal-title":"Journal of Chinese Information Processing"},{"issue":"1","key":"e_1_3_3_17_2","first-page":"92","article-title":"Research and implementation of SVM-based sentiment analysis for Tibetan microblogs","volume":"4","author":"Huang Chenchen","year":"2020","unstructured":"Chenchen Huang, Suolangwangmu Lamuzhuoga, and Qunnuo. 2020. Research and implementation of SVM-based sentiment analysis for Tibetan microblogs. Highland Science Research 4, 1 (2020), 92\u201396.","journal-title":"Highland Science Research"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"issue":"1","key":"e_1_3_3_19_2","first-page":"252","article-title":"Self-attention-based BGRU and CNN for sentiment analysis","volume":"49","author":"Hu Yanli","year":"2022","unstructured":"Yanli Hu, Tanqian Tong, Xiaoyu Zhang, and Juan Peng. 2022. Self-attention-based BGRU and CNN for sentiment analysis. Computer Science 49, 1 (2022), 252\u2013258.","journal-title":"Computer Science"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.572"},{"key":"e_1_3_3_21_2","first-page":"1123","article-title":"Deep learning algorithm applied in Tibetan sentiment analysis","volume":"7","author":"Pu Ciren","year":"2017","unstructured":"Ciren Pu, Jialin Hou, Yue Liu, and Donghai Zhai. 2017. Deep learning algorithm applied in Tibetan sentiment analysis. Journal of Frontiers of Computer Science and Technology 7 (2017), 1123\u20131130.","journal-title":"Journal of Frontiers of Computer Science and Technology"},{"issue":"10","key":"e_1_3_3_22_2","first-page":"56","article-title":"Research on Tibetan micro-blog affective computation based on deep learning algorithm","volume":"29","author":"Sun Benwang","year":"2019","unstructured":"Benwang Sun and Fang Tian. 2019. Research on Tibetan micro-blog affective computation based on deep learning algorithm. Computer Technology and Development 29, 10 (2019), 56\u201358.","journal-title":"Computer Technology and Development"},{"key":"e_1_3_3_23_2","volume-title":"Research on Sentiment Analysis in Tibetan Texts","author":"Quecuo Zhuoma","year":"2020","unstructured":"Zhuoma Quecuo. 2020. Research on Sentiment Analysis in Tibetan Texts. Master's Thesis. Qinghai Normal University, Xining, China."},{"key":"e_1_3_3_24_2","volume-title":"Research on Tibetan Emotion Analysis Method Based on Deep Learning","author":"Zhu Yulei","year":"2023","unstructured":"Yulei Zhu. 2023. Research on Tibetan Emotion Analysis Method Based on Deep Learning. Master's Thesis. Tibetan University, Lhasa, China."},{"issue":"2","key":"e_1_3_3_25_2","first-page":"61","article-title":"Tibetan word segmentation based discriminative classification and reranking","volume":"28","author":"Sun Meng","year":"2014","unstructured":"Meng Sun, Que-Cai-Rang Hua, Zhijie Cai, Wenbin Jiang, Yajuan Lv, and Qun Liu. 2014. Tibetan word segmentation based discriminative classification and reranking. Journal of Chinese Information Processing 28, 2 (2014), 61\u201365.","journal-title":"Journal of Chinese Information Processing"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"e_1_3_3_28_2","first-page":"3937","article-title":"CINO: A Chinese minority pre-trained language model","author":"Yang Ziqing","year":"2022","unstructured":"Ziqing Yang, Zihang Xu, Yiming Cui, Baoxin Wang, Min Lin, Dayong Wu, and Zhigang Chen. 2022. CINO: A Chinese minority pre-trained language model. In Proceedings of the 29th International Conference on Computational Linguistics. 3937\u20133949.","journal-title":"Proceedings of the 29th International Conference on Computational Linguistics"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.611"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1144"},{"key":"e_1_3_3_32_2","first-page":"8410","article-title":"PPT: Pre-trained prompt tuning for few-shot learning","author":"Gu Yuxian","year":"2021","unstructured":"Yuxian Gu, Xu Han, Zhiyuan Liu, and Minlie Huang. 2021. PPT: Pre-trained prompt tuning for few-shot learning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 8410\u20138423.","journal-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics"},{"issue":"9","key":"e_1_3_3_33_2","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompt methods in natural language processing","volume":"55","author":"Liu Pengfei","year":"2021","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2021. Pre-train, prompt, and predict: A systematic survey of prompt methods in natural language processing. ACM Computing Surveys 55, 9 (2021), 1\u201335.","journal-title":"ACM Computing Surveys"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_3_35_2","first-page":"1","article-title":"Sentiment classification model based on non-negative sinusoidal positional encoding and hybrid attention mechanism","volume":"18","author":"Zheng Zhichao","year":"2023","unstructured":"Zhichao Zheng, Jindong Chen, and Jian Zhang. 2023. Sentiment classification model based on non-negative sinusoidal positional encoding and hybrid attention mechanism. Computer Engineering and Applications 18 (2023), 1\u201318.","journal-title":"Computer Engineering and Applications"},{"key":"e_1_3_3_36_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998\u20136008."},{"issue":"1","key":"e_1_3_3_37_2","first-page":"124","article-title":"Design and optimization of loss function in fine-grained sentiment and emotion analysis","volume":"38","author":"Ye Shiren","year":"2024","unstructured":"Shiren Ye, Li Ding, Rinku Md. Ali. 2024. Design and optimization of loss function in fine-grained sentiment and emotion analysis. Journal of Chinese Information Processing 38, 1 (2024), 124\u2013134.","journal-title":"Journal of Chinese Information Processing"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698575","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:34Z","timestamp":1750294714000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698575"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"references-count":36,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12,31]]}},"alternative-id":["10.1145\/3698575"],"URL":"https:\/\/doi.org\/10.1145\/3698575","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"2023-02-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}