--- title: "Nigeria — research institutions, scientists and papers" description: "Nigeria: 3 institutions with papers in our library in 3 agglomerations, 3 people with a page, 7 works, 2,517 citations." canonical: "https://research.elamur.ai/free/en/countries/nigeria/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/countries/nigeria/) [home](https://md.research.elamur.ai/free/en/) / [countries](https://md.research.elamur.ai/free/en/countries/) / Nigeria # Nigeria Country 3 institutions in 3 agglomerations · [all countries](https://md.research.elamur.ai/free/en/countries/) [**3** institutions with a page](https://md.research.elamur.ai/free/en/countries/nigeria/#institutions) · [**3** agglomerations](https://md.research.elamur.ai/free/en/countries/nigeria/#agglomerations) · [**3** people with a page](https://md.research.elamur.ai/free/en/countries/nigeria/#authors) · [**7** works in our library](https://md.research.elamur.ai/free/en/countries/nigeria/#works) · [**2,517** citations of their works](https://md.research.elamur.ai/free/en/countries/nigeria/#works) ## About ### Profile Nigeria appears on this site through three universities, each in a different city: [Bayero University Kano](https://md.research.elamur.ai/free/en/universities/bayero-university-kano/) in [Kano](https://md.research.elamur.ai/free/en/agglomerations/kano/), the [University of Ibadan](https://md.research.elamur.ai/free/en/universities/university-of-ibadan/) in [Ibadan](https://md.research.elamur.ai/free/en/agglomerations/ibadan/), and [Ahmadu Bello University](https://md.research.elamur.ai/free/en/universities/ahmadu-bello-university/) in [Zaria](https://md.research.elamur.ai/free/en/agglomerations/zaria/). No research institute, company, hospital or government body in the country has yet entered the collection, so the Nigerian presence here comes entirely from university-based authors. The [Nigerian institutions](https://md.research.elamur.ai/free/en/countries/nigeria/institutions/) and their [agglomerations](https://md.research.elamur.ai/free/en/countries/nigeria/agglomerations/) can be compared with those of [other countries](https://md.research.elamur.ai/free/en/countries/) and with [institutions of every kind](https://md.research.elamur.ai/free/en/orgs/). The body of Nigerian work in our library is small but closely focused. Nearly all of it belongs to [natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/), with a share also filed under [linguistics and languages](https://md.research.elamur.ai/free/en/shelves/linguistics/). The common thread is language technology for African languages, which have few digital resources: building datasets, checking their quality, and testing how well models for translation, entity recognition and sentiment analysis serve these languages. Because the set of works is compact, each paper shapes the overall picture, and the profile may shift as more Nigerian work is added. ### History Among the works here, Nigerian research begins in 2020 with a study of participatory machine translation for African languages, written by a large community of authors and connected on this site to Bayero University Kano. That paper set the tone for what followed: research on African languages driven by researchers who speak them, rather than by outside groups alone. In 2021 two widely taken-up papers followed. One was an audit of large web-crawled multilingual datasets, linked to both the Kano and Ibadan universities. The other was the first MasakhaNER dataset for named entity recognition in African languages, also linked to both. These works moved the line from translation into data quality and information extraction. The year 2022 is the busiest on this site. It brought a study of African news translation with pre-trained models, connected to Ibadan, and two works connected to Ahmadu Bello University in Zaria: the second MasakhaNER release and the NaijaSenti sentiment corpus for Nigerian languages. With NaijaSenti, the work moved into sentiment analysis, and its Nigerian focus became explicit in the title itself. The latest work here is dated 2026. It is a multilingual interpretability dataset for sentiment analysis that includes Hausa, and it is linked to Bayero University Kano. It carries the earlier sentiment work toward the question of why models reach their judgements. ### Research profile The most common topic among the Nigerian works is [multilingual and cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/). This covers models and resources that span many languages at once. The audit of web-crawled corpora belongs here, as does the news translation study, which looks at how large multilingual systems handle African languages that are thinly represented in their training text. [Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) form a second strand, running through most of the collection even where it is not the main label. The dataset audit argues that poorly checked data releases can make progress on such languages look better than it is. The participatory translation study frames the shortage of tools for African languages as a matter of social and historical inequity, not only of missing technical resources. [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) is represented by the two MasakhaNER papers. The first describes the typology and writing systems of the languages it covers, including scripts and tone, alongside baseline results. The second builds a larger human-annotated corpus of news text in many Sub-Saharan African languages. It studies transfer learning that takes African languages as its starting point. [Sentiment and emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) is the newest major line. NaijaSenti offers human-labelled tweets in Nigerian languages, which its authors present as the first resource of its kind and scale. The later SAINT dataset adds span-level annotation in Amharic, English, German and Hausa. That work touches on [interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/) and, through Amharic, on [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/). [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) is a smaller line here but an early one. It is carried by the participatory study and by the news translation paper, which shows that a modest amount of high-quality translated text can greatly help pre-trained models for African languages. ### Leading scientists [Shamsuddeen Hassan Muhammad](https://md.research.elamur.ai/free/en/authors/shamsuddeen-hassan-muhammad/), of Bayero University Kano, comes first among the Nigerian researchers on this site, and their work here has been cited more than that of any other Nigerian author. Muhammad is the first author of the NaijaSenti corpus and appears across the wider body of African-language work in the collection. That work spans sentiment resources, entity recognition and multilingual datasets. [Idris Abdulmumin](https://md.research.elamur.ai/free/en/authors/idris-abdulmumin/) is connected on this site to Ahmadu Bello University, and is also named among the people of Bayero University Kano. The Zaria works with which Abdulmumin is associated are the second MasakhaNER corpus and NaijaSenti, both from 2022. They place Abdulmumin's research in entity recognition and sentiment analysis for African languages. [Ibrahim Sa'id Ahmad](https://md.research.elamur.ai/free/en/authors/ibrahim-sa-id-ahmad/), also of Bayero University Kano, is the third Nigerian researcher with a profile confirmed at a Nigerian institution. Ahmad's work here belongs to the same Kano strand of research on African and Nigerian languages. Among the people associated with Bayero University Kano, the site also names [Sukairaj Hafiz Imam](https://md.research.elamur.ai/free/en/authors/sukairaj-hafiz-imam/). The University of Ibadan has no author whose profile is confirmed there. Its works are nonetheless connected to several researchers: [Jesujoba Alabi](https://md.research.elamur.ai/free/en/authors/jesujoba-alabi/), a co-author of the news translation study, along with [Tajuddeen Gwadabe](https://md.research.elamur.ai/free/en/authors/tajuddeen-gwadabe/) and [Iain Marshall](https://md.research.elamur.ai/free/en/authors/iain-marshall/). ### Landmark works The most cited Nigerian-linked work in our library is [Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets](https://md.research.elamur.ai/free/en/papers/kreutzer-2021-quality-glance-audit-web-crawled/) (2021), by Julia Kreutzer, Isaac Caswell, Lisa Wang and many co-authors. It checked large public multilingual corpora by hand. It warned that low-quality releases risk overstating what systems can do in under-resourced languages. Among the works here, it is also the one most often cited by other papers in the collection. Close behind is [MasakhaNER: Named Entity Recognition for African Languages](https://md.research.elamur.ai/free/en/papers/adelani-2021-masakhaner-named-entity-recognition-african/) (2021), led by David Ifeoluwa Adelani with Jade Abbott, Graham Neubig and others. It offered annotated entity data for a set of African languages. It described each language's structure and orthography and reported baseline systems. The earliest landmark here is [Participatory Research for Low-resourced Machine Translation](https://md.research.elamur.ai/free/en/papers/nekoto-2020-participatory-research-low-resourced-machine/) (2020), with Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila and a wide group of contributors. It presented a community-based way of building translation resources and connected the technical gap to its social roots. [A Few Thousand Translations Go a Long Way!](https://md.research.elamur.ai/free/en/papers/adelani-2022-few-thousand-translations-go-long/) (2022), by Adelani, Jesujoba Oluwadara Alabi, Angela Fan and colleagues, tested pre-trained translation models on African news. It found that a small curated parallel corpus brings large gains. [MasakhaNER 2.0](https://md.research.elamur.ai/free/en/papers/adelani-2022-masakhaner-2-0-africa-centric/) (2022), with Adelani, Neubig, Sebastian Ruder and others, widened the entity recognition effort and studied which source languages transfer best. [NaijaSenti](https://md.research.elamur.ai/free/en/papers/muhammad-2022-naijasenti-nigerian-twitter-sentiment-corpus/) (2022), led by Muhammad with Adelani, Ruder and others, built a labelled Twitter sentiment resource for Nigerian languages. The most recent work, [SAINT](https://md.research.elamur.ai/free/en/papers/yimam-2026-saint-multilingual-span-level-interpretability/) (2026), by Seid Muhie Yimam, Tadesse Destaw Belay, Robert Geislinger and others, adds span-level explanations for sentiment labels in its four languages. ### Labs and units On this site Nigeria is represented by universities only. Bayero University Kano is linked to the largest set of works and carries the most citation weight. Its work covers translation, data auditing, entity recognition and interpretable sentiment analysis. The University of Ibadan follows closely, with a smaller set of works that have drawn heavy attention, focused on dataset quality, entity recognition and news translation. Ahmadu Bello University in Zaria contributes a distinct share centred on the 2022 entity and sentiment corpora. No departments or smaller units are shown for the Nigerian institutions. ### Collaborations Every Nigerian-linked work here is a team effort with many authors. The co-authors who recur most often are David Ifeoluwa Adelani, who leads several of the works, along with Graham Neubig and Sebastian Ruder. The works also bring together researchers named alongside them, such as Jade Abbott, Vukosi Marivate, Angela Fan, Julia Kreutzer and Isaac Caswell. The SAINT dataset connects the Nigerian line with work on Amharic and German through Yimam, Belay and Geislinger. Within Nigeria, the links between universities are clear. The dataset audit and the first MasakhaNER paper are each connected to both Bayero University Kano and the University of Ibadan. Idris Abdulmumin connects Zaria with Kano. Taken together, the three universities appear here less as separate programmes than as nodes in one shared effort on African-language technology. The site shows no companies in Nigeria, so links between industry and academia cannot be traced here. ### Timeline In 2020 the Nigerian line on this site opens with the participatory machine translation study, connected to Kano. It frames African-language technology as community work. In 2021 the most cited works arrive. These are the audit of web-crawled multilingual data and the first MasakhaNER corpus, both shared between Kano and Ibadan. The research widens from translation into data quality and entity recognition. In 2022 the output is at its broadest. Ibadan contributes the news translation study, and Zaria contributes MasakhaNER 2.0 and NaijaSenti. Sentiment analysis of Nigerian languages becomes a line of its own. In 2026 the SAINT dataset, connected to Kano, extends the sentiment work into span-level interpretability across Hausa, Amharic, English and German. It is the most recent stage of Nigerian research visible among the works here. ## Where ## Agglomerations (3) 1. [**Kano**1 institution*1,209 citations*](https://md.research.elamur.ai/free/en/agglomerations/kano/) 2. [**Ibadan**1 institution*1,031 citations*](https://md.research.elamur.ai/free/en/agglomerations/ibadan/) 3. [**Zaria**1 institution*277 citations*](https://md.research.elamur.ai/free/en/agglomerations/zaria/) ## Institutions (3) ### 🎓 Universities (3) **[Bayero University Kano](https://md.research.elamur.ai/free/en/universities/bayero-university-kano/)**University · [Kano](https://md.research.elamur.ai/free/en/agglomerations/kano/), Nigeria*4 works · 1,209 citations* **[University of Ibadan](https://md.research.elamur.ai/free/en/universities/university-of-ibadan/)**University · [Ibadan](https://md.research.elamur.ai/free/en/agglomerations/ibadan/), Nigeria*3 works · 1,031 citations* **[Ahmadu Bello University](https://md.research.elamur.ai/free/en/universities/ahmadu-bello-university/)**University · [Zaria](https://md.research.elamur.ai/free/en/agglomerations/zaria/), Nigeria*2 works · 277 citations* ## People (3) Authors with a page confirmed at its institutions, the most cited first. [🧑‍🔬**Shamsuddeen Hassan Muhammad** Bayero University Kano 6 papers here · 2,281 citations](https://md.research.elamur.ai/free/en/authors/shamsuddeen-hassan-muhammad/) · [🧑‍🔬**Idris Abdulmumin** Ahmadu Bello University 2 papers here · 802 citations](https://md.research.elamur.ai/free/en/authors/idris-abdulmumin/) · [🧑‍🔬**Ibrahim Sa'id Ahmad** Bayero University Kano 2 papers here · 291 citations](https://md.research.elamur.ai/free/en/authors/ibrahim-sa-id-ahmad/) ## Works in our library (7) Works of its institutions, the most cited first. 1. [**Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets**Julia Kreutzer, Isaac Caswell, Lisa Wang, et al.*2021 · 447 citations*](https://md.research.elamur.ai/free/en/papers/kreutzer-2021-quality-glance-audit-web-crawled/) 2. [**MasakhaNER: Named Entity Recognition for African Languages**David Ifeoluwa Adelani, Jade Abbott, Graham Neubig, et al.*2021 · 429 citations*](https://md.research.elamur.ai/free/en/papers/adelani-2021-masakhaner-named-entity-recognition-african/) 3. [**Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages**Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila, et al.*2020 · 333 citations*](https://md.research.elamur.ai/free/en/papers/nekoto-2020-participatory-research-low-resourced-machine/) 4. [**A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation**David Ifeoluwa Adelani, Jesujoba Oluwadara Alabi, Angela Fan, et al.*2022 · 155 citations*](https://md.research.elamur.ai/free/en/papers/adelani-2022-few-thousand-translations-go-long/) 5. [**MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition**David Ifeoluwa Adelani, Graham Neubig, Sebastian Ruder, et al.*2022 · 150 citations*](https://md.research.elamur.ai/free/en/papers/adelani-2022-masakhaner-2-0-africa-centric/) 6. [**NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis**Shamsuddeen Hassan Muhammad, David Ifeoluwa Adelani, Sebastian Ruder, et al.*2022 · 127 citations*](https://md.research.elamur.ai/free/en/papers/muhammad-2022-naijasenti-nigerian-twitter-sentiment-corpus/) 7. [**SAINT: Multilingual Span-Level Interpretability for Sentiment Analysis**Seid Muhie Yimam, Tadesse Destaw Belay, Robert Geislinger, et al.*2026*](https://md.research.elamur.ai/free/en/papers/yimam-2026-saint-multilingual-span-level-interpretability/) ## Concepts, shelves and topics Of its works in our library: the number of works on each and its rating among them. 💡 Concepts 1[Named entity recognition · 1 work · 20.7](https://md.research.elamur.ai/free/en/concepts/named-entity-recognition/) 📚 Shelves 2[Natural language processing · 5 works · 84.8](https://md.research.elamur.ai/free/en/shelves/nlp/) · [Linguistics & languages · 2 works · 11.3](https://md.research.elamur.ai/free/en/shelves/linguistics/) 🧭 Topics 7[Named entity recognition · 2 works · 33.0](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) · [Multilingual & cross-lingual NLP · 3 works · 26.8](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Low-resource languages · 2 works · 9.1](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · [Machine translation · 1 work · 9.1](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Sentiment & emotion · 2 works · 5.6](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Interpretability · 1 work · 0.0](https://md.research.elamur.ai/free/en/topics/interpretability/) · [Semitic languages · 1 work · 0.0](https://md.research.elamur.ai/free/en/topics/semitic-languages/) ## Works by year ### 2020s [**2026** 1 work](https://md.research.elamur.ai/free/en/papers/yimam-2026-saint-multilingual-span-level-interpretability/) · [**2022** 3 works](https://md.research.elamur.ai/free/en/countries/nigeria/year/2022/) · [**2021** 2 works](https://md.research.elamur.ai/free/en/countries/nigeria/year/2021/) · [**2020** 1 work](https://md.research.elamur.ai/free/en/papers/nekoto-2020-participatory-research-low-resourced-machine/) - [← back to](https://md.research.elamur.ai/free/en/countries/) — countries