--- title: "Weizhou Shen — author profile and papers" description: "Weizhou Shen, Alibaba Group (Cayman Islands): 2 papers on Elamur Research (2020–2021), h-index 15 — affiliations, topics, co-authors and who cites them…" canonical: "https://research.elamur.ai/free/en/authors/weizhou-shen/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/weizhou-shen/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Weizhou Shen # Weizhou Shen Weizhou Shen works on sentiment and emotion analysis in natural language processing. Their papers here date from 2020 and 2021 and share an approach to structure. Instead of letting a model attend loosely across a text, they build graphs that encode which parts of a sentence or conversation should inform one another. 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 most cited paper, [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), deals with reviews in which one sentence names several aspects that carry conflicting opinions. In such cases attention-based models often pair an aspect with the wrong opinion word. The paper argues that syntactic structure shaped around the task can correct these mismatches. The second, [Directed Acyclic Graph Network for Conversational Emotion Recognition](https://md.research.elamur.ai/free/en/papers/shen-2021-directed-acyclic-graph-network-conversational/) (2021), assigns an emotion to each utterance in a dialogue. It brings together two families of models. Graph-based methods see only a fixed local window and lose order and distant context. Recurrent methods follow the history but draw on just a few earlier turns at each step. The paper merges their strengths by representing a conversation as a directed acyclic graph in which information passes only forward in time. The 2021 conversation paper is the newest work here and moves from single review sentences to multi-turn dialogue, where context and the order of turns matter. Shen is currently affiliated with Alibaba Group in Hangzhou, after earlier papers from Sun Yat-sen University in Guangzhou between 2019 and 2024. Co-authors who appear on more than one paper include [Xiaojun Quan](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/) and [Yunyi Yang](https://md.research.elamur.ai/free/en/authors/yunyi-yang/). 2 papers on this site · 2020–2021 current affiliation [Alibaba Group (Cayman Islands)](https://md.research.elamur.ai/free/en/companies/alibaba-group-cayman-islands/), George Town, Cayman Islands; [Alibaba Group (China)](https://md.research.elamur.ai/free/en/companies/alibaba-group/), Hangzhou, China Weizhou Shen 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 [Xiaojun Quan](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/), [Yunyi Yang](https://md.research.elamur.ai/free/en/authors/yunyi-yang/), [Kai Wang](https://md.research.elamur.ai/free/en/authors/kai-wang/). [OpenAlex](https://openalex.org/A5108481711) · [ORCID](https://orcid.org/0000-0001-9180-0043) · [**h-index 15**](https://openalex.org/authors/A5108481711) · [46 works](https://openalex.org/works?filter=author.id:A5108481711) · [3 453 citations](https://openalex.org/works?filter=author.id:A5108481711&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/weizhou-shen/#papers) · [232 citations in our library](https://md.research.elamur.ai/free/en/authors/weizhou-shen/cited-by/) · 5 more works in our library 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=Weizhou+Shen) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Weizhou+Shen) · [dblp](https://dblp.org/search?q=Weizhou+Shen) · [ACL Anthology](https://aclanthology.org/search/?q=Weizhou+Shen) ## Affiliations - [Alibaba Group (China)](https://md.research.elamur.ai/free/en/companies/alibaba-group/) · Hangzhou, China —current · 2023–2026 on 10 papers - [Alibaba Group (Cayman Islands)](https://md.research.elamur.ai/free/en/companies/alibaba-group-cayman-islands/) · George Town, Cayman Islands —current · 2025–2026 on 5 papers - [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) · Guangzhou, China —2019–2024 on 12 papers - [Nanjing University](https://md.research.elamur.ai/free/en/universities/nanjing-university/) · Nanjing, China —1992–2017 on 13 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution 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. ## Also in our library 5 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 4 co-authors with a page, the most papers together first. - [Xiaojun Quan](https://md.research.elamur.ai/free/en/authors/xiaojun-quan/) ×2 - [Yunyi Yang](https://md.research.elamur.ai/free/en/authors/yunyi-yang/) ×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 232 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/weizhou-shen/cited-by/).