--- title: "Deepanway Ghosal — author profile and papers" description: "Deepanway Ghosal: 2 papers on Elamur Research (2019–2020), h-index 19 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/deepanway-ghosal/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/deepanway-ghosal/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Deepanway Ghosal # Deepanway Ghosal Deepanway Ghosal works on how emotion is handled in conversational language processing. Ghosal's two papers here, from 2019 and 2020, sit where [sentiment and emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) analysis meets [dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/). One asks how a model can tell which emotion an utterance in a conversation expresses. The other asks how a dialogue system can answer a speaker with a fittingly empathetic reply. Both use neural architectures that model the structure of a conversation rather than treating each sentence in isolation. The more cited of the two is [DialogueGCN](https://md.research.elamur.ai/free/en/papers/ghosal-2019-dialoguegcn-graph-convolutional-neural-network/) (2019), which addresses emotion recognition in conversation. Recurrent models tend to lose track of distant context, so the paper instead represents a dialogue as a directed graph. Each utterance is a node, connected to nearby turns before and after it. The edges are typed by the pair of speakers involved and by direction in time. This lets the model capture both how participants influence one another and how a single speaker's emotional state persists. Utterance features come from a convolutional text encoder and a bidirectional GRU, and these feed a relational graph network. The later paper, [MIME](https://md.research.elamur.ai/free/en/papers/majumder-2020-mime-mimicking-emotions-empathetic-response/) (2020), moves from recognising emotion to producing it. It argues that earlier empathetic generators placed all emotions in a single undifferentiated group. It proposes instead that a listener partly mirrors the speaker's feeling, and that positive and negative emotions are handled differently. Positive remarks tend to draw positive answers, while negative ones call for agreement blended with reassurance or hope. Most of Ghosal's bylines list the Singapore University of Technology and Design (2019–2025), with earlier papers from the Indian Institute of Technology Patna (2017–2019). Co-authors on the papers here include [Soujanya Poria](https://md.research.elamur.ai/free/en/authors/soujanya-poria/) and [Navonil Majumder](https://md.research.elamur.ai/free/en/authors/navonil-majumder/), each on two papers, along with [Alexander Gelbukh](https://md.research.elamur.ai/free/en/authors/alexander-gelbukh/) and [Rada Mihalcea](https://md.research.elamur.ai/free/en/authors/rada-mihalcea/). 2 papers on this site · 2019–2020 Deepanway Ghosal has 2 papers on this site, in 2019–2020, 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 [Alexander Gelbukh](https://md.research.elamur.ai/free/en/authors/alexander-gelbukh/), [Navonil Majumder](https://md.research.elamur.ai/free/en/authors/navonil-majumder/), [Soujanya Poria](https://md.research.elamur.ai/free/en/authors/soujanya-poria/). [OpenAlex](https://openalex.org/A5086877005) · [ORCID](https://orcid.org/0000-0002-3858-4449) · [**h-index 19**](https://openalex.org/authors/A5086877005) · [67 works](https://openalex.org/works?filter=author.id:A5086877005) · [2 773 citations](https://openalex.org/works?filter=author.id:A5086877005&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/deepanway-ghosal/#papers) · [214 citations in our library](https://md.research.elamur.ai/free/en/authors/deepanway-ghosal/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=Deepanway+Ghosal) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Deepanway+Ghosal) · [dblp](https://dblp.org/search?q=Deepanway+Ghosal) · [ACL Anthology](https://aclanthology.org/search/?q=Deepanway+Ghosal) ## Affiliations - [Singapore University of Technology and Design](https://md.research.elamur.ai/free/en/universities/singapore-university-of-technology-and-design/) · Singapore, Singapore —2019–2025 on 33 papers - [Google (United States)](https://md.research.elamur.ai/free/en/companies/google/) · Mountain View, United States —2023–2025 on 2 papers - [University of Michigan](https://md.research.elamur.ai/free/en/universities/university-of-michigan/) · Ann Arbor, United States —2022–2023 on 2 papers - [Instituto Politécnico Nacional](https://md.research.elamur.ai/free/en/universities/instituto-politecnico-nacional/) · Mexico City, Mexico —2020 on 2 papers - [Indian Institute of Technology Patna](https://md.research.elamur.ai/free/en/universities/indian-institute-of-technology-patna/) · Patna, India —2017–2019 on 7 papers - [Nanyang Technological University](https://md.research.elamur.ai/free/en/universities/nanyang-technological-university/) · Singapore, Singapore —2018–2019 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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 [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/majumder-2020-mime-mimicking-emotions-empathetic-response/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/ghosal-2019-dialoguegcn-graph-convolutional-neural-network/) ## Papers The most cited first (OpenAlex and our library). 1. **[DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation](https://md.research.elamur.ai/free/en/papers/ghosal-2019-dialoguegcn-graph-convolutional-neural-network/)** *(2019 · 850 citations)* DialogueGCN targets emotion recognition in conversation (ERC). Earlier RNN-based approaches such as DialogueRNN struggle to carry context across distant utterances and do not explicitly encode who said what or where an utterance sits relative to the target. The authors represent each dialogue as a directed graph.… 2. **[MIME: MIMicking Emotions for Empathetic Response Generation](https://md.research.elamur.ai/free/en/papers/majumder-2020-mime-mimicking-emotions-empathetic-response/)** *(2020 · 277 citations)* The paper tackles empathetic response generation in dialogue. The authors argue that earlier systems, such as the state-of-the-art MoEL, treat all emotions as one flat, uniform set. MIME instead assumes that empathetic listeners partly copy the speaker's emotion, and that how much they copy depends on whether that… ## Co-authors here 4 co-authors with a page, the most papers together first. - [Alexander Gelbukh](https://md.research.elamur.ai/free/en/authors/alexander-gelbukh/) ×2 - [Navonil Majumder](https://md.research.elamur.ai/free/en/authors/navonil-majumder/) ×2 - [Soujanya Poria](https://md.research.elamur.ai/free/en/authors/soujanya-poria/) ×2 - [Rada Mihalcea](https://md.research.elamur.ai/free/en/authors/rada-mihalcea/) ## Cited by Papers of our library cite their works 214 times (of the 140 884 papers whose bibliographies we read); [9 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/deepanway-ghosal/cited-by/).