--- title: "Yunyi Yang — author profile and papers" description: "Yunyi Yang, Beijing Jiaotong University: 2 papers on Elamur Research (2020–2021), h-index 11 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/yunyi-yang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yunyi-yang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Yunyi Yang # Yunyi Yang Yunyi Yang works on sentiment and emotion analysis in natural language processing, building neural models on graphs. Both papers here ask how a model can find the context that matters for a judgement. In a review, that means tying each opinion word to the aspect it describes. In a dialogue, it means picking out the earlier turns that shape the emotion of the current one. In each case the network is given an explicit structure, syntactic in one paper and temporal in the other, instead of relying on attention alone. The work falls under [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) and [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/). The more widely cited of the two is [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wang-2020-relational-graph-attention-network-aspect/) (2020). It addresses reviews in which one sentence names several aspects carrying opposite opinions. Attention-based models often pair an aspect with the wrong opinion word in such sentences. The paper argues that syntactic information shaped for the task can correct this. The later paper, [Directed Acyclic Graph Network for Conversational Emotion Recognition](https://md.research.elamur.ai/free/en/papers/shen-2021-directed-acyclic-graph-network-conversational/) (2021), moves from reviews to dialogue, where every utterance receives an emotion label. Graph-based models of the time looked only at a fixed window of neighbouring utterances, which cost them distant context and turn order. Recurrent models kept a running history, but each step drew on just a few recent turns. The paper joins the two approaches by modelling a conversation as a directed acyclic graph through which information flows only forward in time. Yang is currently affiliated with Beijing Jiaotong University and Xi'an Jiaotong University. Earlier bylines from 2019 to 2022 list Sun Yat-sen University in Guangzhou. [Weizhou Shen](https://md.research.elamur.ai/free/en/authors/weizhou-shen/) and [Xiaojun Quan](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/) co-wrote both papers here, and [Kai Wang](https://md.research.elamur.ai/free/en/authors/kai-wang/) and [Rui Wang](https://md.research.elamur.ai/free/en/authors/rui-wang/) each appear on one. 2 papers on this site · 2020–2021 current affiliation [Beijing Jiaotong University](https://md.research.elamur.ai/free/en/universities/beijing-jiaotong-university/), Beijing, China; [Xi'an Jiaotong University](https://md.research.elamur.ai/free/en/universities/xi-an-jiaotong-university/), Xi'an, China Yunyi Yang has 2 papers on this site, in 2020–2021, most of them on [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/), [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/); often with [Weizhou Shen](https://md.research.elamur.ai/free/en/authors/weizhou-shen/), [Xiaojun Quan](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/), [Kai Wang](https://md.research.elamur.ai/free/en/authors/kai-wang/). [OpenAlex](https://openalex.org/A5103982594) · [ORCID](https://orcid.org/0009-0003-2964-5582) · [**h-index 11**](https://openalex.org/authors/A5103982594) · [27 works](https://openalex.org/works?filter=author.id:A5103982594) · [1 329 citations](https://openalex.org/works?filter=author.id:A5103982594&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/yunyi-yang/#papers) · [180 citations in our library](https://md.research.elamur.ai/free/en/authors/yunyi-yang/cited-by/) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Yunyi+Yang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Yunyi+Yang) · [dblp](https://dblp.org/search?q=Yunyi+Yang) · [ACL Anthology](https://aclanthology.org/search/?q=Yunyi+Yang) ## Affiliations - [Beijing Jiaotong University](https://md.research.elamur.ai/free/en/universities/beijing-jiaotong-university/) · Beijing, China —current · 2007–2026 on 5 papers - [Xi'an Jiaotong University](https://md.research.elamur.ai/free/en/universities/xi-an-jiaotong-university/) · Xi'an, China —current · 2023–2026 on 2 papers - [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) · Guangzhou, China —2019–2022 on 8 papers - [Baidu (China)](https://md.research.elamur.ai/free/en/companies/baidu/) · Beijing, China —2021 on 2 papers - [Northwestern Polytechnical University](https://md.research.elamur.ai/free/en/universities/northwestern-polytechnical-university/) · Xi'an, China —2015–2016 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 more institutions on single bylines are not listed. ## Topics [Sentiment & emotion 2](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Dialogue systems 1](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) ## Works by year ### 2020s [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/shen-2021-directed-acyclic-graph-network-conversational/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/wang-2020-relational-graph-attention-network-aspect/) ## Papers The most cited first (OpenAlex and our library). 1. **[Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wang-2020-relational-graph-attention-network-aspect/)** *(2020 · 775 citations)* Aspect-based sentiment analysis (ABSA) assigns a sentiment polarity to each aspect mentioned in a review. This is difficult when one sentence contains several aspects with opposing opinions, because attention-based models often link an aspect to the wrong opinion word. The authors argue that explicit syntax focused… 2. **[Directed Acyclic Graph Network for Conversational Emotion Recognition](https://md.research.elamur.ai/free/en/papers/shen-2021-directed-acyclic-graph-network-conversational/)** *(2021 · 344 citations)* The paper tackles emotion recognition in conversation (ERC), where each utterance in a dialogue gets an emotion label. ## Co-authors here 4 co-authors with a page, the most papers together first. - [Weizhou Shen](https://md.research.elamur.ai/free/en/authors/weizhou-shen/) ×2 - [Xiaojun Quan](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/) ×2 - [Kai Wang](https://md.research.elamur.ai/free/en/authors/kai-wang/) - [Rui Wang](https://md.research.elamur.ai/free/en/authors/rui-wang/) ## Cited by Papers of our library cite their works 180 times (of the 140 884 papers whose bibliographies we read); [1 citing paper with a page here →](https://md.research.elamur.ai/free/en/authors/yunyi-yang/cited-by/).