According to the latest census data, Lakshadweep, the island union territory had the highest share of Muslim population in the country, where 97 percent of its population identified as followers of the Islamic faith. Jammu & Kashmir ranked second at 68 percent during the same time period. With almost all major religions being practiced throughout the country, India is known for its religious diversity. Islam makes up the highest share among minority faiths in the country.

In 2020, Indonesia recorded the largest population of Muslims worldwide, with around 239 million. This was followed with around 226.88 million Muslims in Pakistan and 213 million Muslims in India.

Islam is the major religion in many African countries, especially in the north of the continent. In Comoros, Libya, Western Sahara, at least 99 percent of the population was Muslim as of 202. These were the highest percentages on the continent. However, also in many other African nations, the majority of the population was Muslim. In Egypt, for instance, Islam was the religion of 79 percent of the people. Islam and other religions in Africa Africa accounts for an important share of the world’s Muslim population. As of 2019, 16 percent of the Muslims worldwide lived in Sub-Saharan Africa, while 20 percent of them lived in the Middle East and North Africa (MENA) region. Together with Christianity, Islam is the most common religious affiliation in Africa, followed by several traditional African religions. Although to a smaller extent, numerous other religions are practiced on the continent: these include Judaism, the Baha’i Faith, Hinduism, and Buddhism. Number of Muslims worldwide Islam is one of the most widespread religions in the world. There are approximately 1.9 billion Muslims globally, with the largest Muslim communities living in the Asia-Pacific region. Specifically, Indonesia hosts the highest number of Muslims worldwide, amounting to over 200 million, followed by India, Pakistan, and Bangladesh. Islam is also present in Europe and America. The largest Islamic communities in Europe are in France (5.72 million), Germany (4.95 million), and the United Kingdom (4.13 million). In the United States, there is an estimated number of around 3.45 million Muslims.

With almost all major religions being practiced throughout the country, India is known for its religious diversity. Islam makes up the highest share among minority faiths in the country. According to the Indian census of 2011, the Muslim population in Uttar Pradesh more than 35 million, making it the state with the most Muslims.

Socio-economic conditions of Muslims
Muslims seem to lag behind every other religious community in India in terms of living standards, financial stability, education and other aspects, thereby showing poor performance in most of the fields. According to a national survey, 17 percent of the Muslims were categorized under the lowest wealth index, which indicates poor socio-economic conditions.

Growth of Muslim population in India
Islam is one of the fastest-growing religions worldwide. According to India’s census, the Muslim population has witnessed a negative decadal growth of more than 16 percent from 1951 to 1960, presumably due to the partitions forming Pakistan and Bangladesh. The population showed a positive and steady growth since 1961, making up 14 percent of the total population of India . Even though people following Islam were estimated to grow significantly, they would still remain a minority in India compared to 1.3 billion Hindus by 2050.

In 2024, Nigeria had the largest Muslim population in Africa, with around 105 million people who belonged to an Islamic denomination. Egypt and Algeria followed with 90.4 million and 39.4 million Muslims, respectively. Muslims have a significant presence in Africa, with an estimated 50 percent of the continent's population identifying as Muslim. The spread of Islam in Africa began in the 7th century with the arrival of Arab traders, and it continued through Islamic scholars and missionaries.

India Census: Population: by Religion: Muslim: Urban data was reported at 68,740,419.000 Person in 2011. This records an increase from the previous number of 49,393,496.000 Person for 2001. India Census: Population: by Religion: Muslim: Urban data is updated yearly, averaging 59,066,957.500 Person from Mar 2001 (Median) to 2011, with 2 observations. The data reached an all-time high of 68,740,419.000 Person in 2011 and a record low of 49,393,496.000 Person in 2001. India Census: Population: by Religion: Muslim: Urban data remains active status in CEIC and is reported by Census of India. The data is categorized under India Premium Database’s Demographic – Table IN.GAE001: Census: Population: by Religion.

Religion and Bangladesh

Religion in Bangladesh is a sensitive issue, mostly because Bangladesh is officially a secular state but recognizes Islam as an official, state religion. Historically and doctrinally, Islamic scholars don’t accept nations that are secular because they think that religion, society and private life are all part of the great community they like to call ‘umma’.

The main religion in Bangladesh is Islam because it is practiced by almost 90 percent of the country’s population. The rest of 10 percent adhere to Hinduism. The type of Islam that is practiced in Bangladesh is Sunni Islam with a lot of Sufi influences. Sunni is the most numerous branch of Islam in the world. Countries like Egypt and Saudi Arabia have Sunni majority populations. The Sufi practices that influence the Islamic religion in Bangladesh are commonly known as mysticism. Sufi followers are poor men that don’t eat, don’t drink and spend their days in deep prayer in order to achieve spiritual connection with God.

Bangladesh has the fourth largest Muslim population in the world, with over 130 million followers, right after Indonesia, Pakistan and India. In its constitution, Bangladesh is recognized as a secular state. For a short period of time, when Bangladesh was under Pakistani rule, Islam was made the state’s official religion. But the Supreme Court or High Court of Bangladesh ruled that Bangladesh must return to the principles of the 1972 constitution, meaning that it mustn’t have an official religion.

The problem with Islam gaining too much power in Bangladesh is that it unbalances the genders issues. Islamic edicts or fatwas have been issued mostly against women by religious courts as punishments for their nonreligious behavior. Global NGO’s are fighting such edicts in order to maintain a fair judgment when it comes to men and women. Bangladesh is a country where gender issues, as well as religious issues are very sensitive subjects.

In 2020, Mexico had a Muslim population of 7,982 people. Mexico City, with 1,636, was the state with the biggest Muslim community in the country. Mexico State was the only other federal entity with more than 1,000 Muslims.

Mali is a predominantly Muslim country with 94.84 percent of the population belonging to Islam. Of that 94.84 percent, only 0.8 percent is Shi’a versus the greater majority of Sunni Muslims in the country. While most of the population is Muslim, a small minority practice other religions as well; 2.37 percent Christianity, 2.02 percent Animist, 0.04 percent Other, 0.45 percent Atheist/Agnostic, and 0.28 percent Undeclared. Of the 2.37 percent of Christians in Mali, the majority of those are Roman Catholic. The Catholic Church has six dioceses that make up less than two percent of Mali’s population. Mali is typically defined as a secular state, with a constitution and code of laws that protect the public’s right for religious freedom and practice.

While the Malian government is officially secular, it frequently consults the moderate High Council of Islam (HCIM) and the Committee of Wise Men on controversial social issues of national scope. The HCIM is an umbrella organization with representatives from all significant Muslim organizations in-country as well as over 160 non-governmental organizations. The Committee of Wise Men includes the Catholic Archbishop and prominent Malian Protestant and Muslim leaders. In an effort to enshrine its commitment to multi-faith democracy, the Malian government has declared a diverse set of religious holidays as national holidays, including Mawloud, the Prophet’s Baptism, Easter Monday, Eid al- Fitf, Tabaski, and Christmas.

Religion is not taught in any public school in Mali. There are some private schools and madrasas that do offer both Christian and Islamic teachings in addition to the state-mandated secular curriculum. In Mali, most madrasas are located in the south in areas such as Sikasso (600), Segou (428), and Bamako (268). In the northern regions of Mali there are a little over 300 madrasas.

In recent months, a loose coalition of militant Tuareg and Islamist groups, including al-Qaeda in the Islamic Maghreb (AQIM), Ansar Dine, the Movement for Unity and Jihad in West Africa (MUJAO), and the Azawad National Liberation Movement (MNLA), has taken over northern Mali with the goal of forming an Islamic state in the Trans-Sahara region. Areas under militant control have seen the imposition of strict Sharia law, including bans on music and severe restrictions on women and practitioners of non-Islamic faiths. In Timbuktu and other northern urban centers, different Islamic groups have destroyed numerous ancient Sufi mosques, tombs, and other artifacts in an effort to purge the region of “heretical” faiths.

Census: Population: by Religion: Muslim: Karnataka: Female data was reported at 3,885,194.000 Person in 03-01-2011. This records an increase from the previous number of 3,160,545.000 Person for 03-01-2001. Census: Population: by Religion: Muslim: Karnataka: Female data is updated decadal, averaging 3,522,869.500 Person from Mar 2001 (Median) to 03-01-2011, with 2 observations. The data reached an all-time high of 3,885,194.000 Person in 03-01-2011 and a record low of 3,160,545.000 Person in 03-01-2001. Census: Population: by Religion: Muslim: Karnataka: Female data remains active status in CEIC and is reported by Office of the Registrar General & Census Commissioner, India. The data is categorized under India Premium Database’s Demographic – Table IN.GAE003: Census: Population: by Religion: Muslim.

Roughly 85 percent of Guinea’s population is Muslim, primarily of the Sunni school. Muslims constitute a majority in all four geographic regions. Christians, mostly Roman Catholic, comprise an 8 percent minority and are situated primarily in Conakry and eastern parts of the Forest Region.Other Christian denominations include Anglicans, Baptists, Jehovah's Witnesses, Seventh-Day Adventists, and various evangelical subgroups. Approximately 7 percent of inhabitants, located principally in the Forest Region, adhere exclusively to indigenous religious beliefs. Islam was introduced in Guinea in the 17th century in what is now the country’s northeast. Starting in the late 1720s, the Fulani ethnic group established a theocratic Muslim state in the mountainous Fouta Djallon region. The Fulani created an ethnoreligious social hierarchy which relegated non-Muslims to the lowest rungs of the social ladder. Though the state was ultimately assimilated into Guinea-proper, the Fulani have remained the country’s most ardent Muslim population, ahead of the Mandinka subgroup of the Mandé people. The non-Muslim Soso people were gradually pushed out of the Fouta Djallon due to Fulani oppression. The majority migrated to coastal parts of Lower Guinea between the 17th and 20thcenturies; an area comprised of the prefectures Boke, Boffa, Conakry, Coyah, Dubreka, Fria, Forecariah, Kindia, and Telimele. Roman Catholic missionaries made inroads into Soso communities following their (the Soso’s) establishment of trade ties with Europe. Many Guinean children, particularly in the Fouta Djallon region attend Islamic schools, which combine the government’s secular curriculum with Quranic studies. More devout Muslims student may enroll at a madrassah, or mosque school, which typically forego French for Arabic as the language of instruction, and adhere exclusively to a religious studies curriculum. Though Guinea’s constitution guarantees religious freedom, Islam enjoys demographic, social, and cultural dominance. In the past some Guineans have claimed the government favors Muslims in its policies, citing the cancellation of classes at publicly funded universities in accommodation of Friday prayers. Despite these and other reports of social discrimination against non-Muslims, religious freedoms are generally respected in the country.

In 2016, it was estimated that Birmingham had the largest Muslim population of any local authority in England and Wales at approximately 280 thousand people. Newham and Tower Hamlets, both boroughs of London, had the second and third-largest Muslim populations at 135 and 128 thousand respectively.

According to a survey conducted in 2022, Muslims were the most likely religious group to agree with certain anti-Muslim stereotypes about Muslims living in the United States. 24 percent of surveyed Muslims agreed with the statement that most Muslims living in the United States were more prone to violence than other people, compared to only nine percent of the general public who shared this belief.

Islam and Christianity form the two dominant religions in Nigeria. The basis of traditional religions was systematically exterminated in the religio-cultural life of the Nigerian people after their contact with colonialism. Approximately 90 percent of the Nigerian people have since preferred to be identified with either Islam or Christianity.Nigeria’s contact with Islam predated that of Christianity and European colonialism; its spread was facilitated into Sub-Saharan Africa through trade and commerce. The northern part of Nigeria is symbolic to the history of Islam, as it penetrated the area through the Kanem-Borno Empire in the 11th century before spreading to the other predominately Hausa states. Islam was then introduced into the traditional societies of the Yoruba-speaking people of south-west Nigeria through their established commercial relationship with people of the North, particularly the Nupe and Fulani.Christianity reached Nigeria in the 15th century with the visitation of the Roman and Catholic missionaries to the coastal areas of the Niger-Delta region, although there were few recorded converts and churches built during this period. Christianity soon recorded a boost in the southern region given its opposition to the slave trade and its promotion of Western education. In contrast to the smooth process Christian evangelization underwent in the South, its process in the North was difficult because Islam had already become well-established.Given the philosophy of Islam as a complete way of life for a Muslim, Islam has always been closely attached to politics in Nigeria. The emergence of particular Islamic groups was significantly influenced by international events, particularly the 1979 Iranian revolution and the corresponding disenchantment from the West. These developments shaped Nigerian national politics of the period as Muslims radically redefined their political interests in line with religion and began to clamor for the incorporation of the Sharia legal system into the country’s judicial system. Nigeria then tried to harness opportunities accruable from other Muslim countries by becoming a registered member with the Organization of Islamic Conference (OIC) in 1985. This inflamed Christians and nurtured the fear of domination by their Muslim counterparts and the possibility of a gradual extinction of their religio-political strength in the national political structure. The distinct religious separation has also instigated violence in present-day Nigeria, including the Sharia riot in Kaduna in 2000, ongoing ethno-religious violence in Jos since 2001, and the 2011 post-election violence that erupted in some northern states. Nigerians’ continued loyalty to religion compared to that of the country continues to sustain major political debate, conflict, and violent outbreaks between populations of the two faiths.

ISO3 - International Organization for Standardization 3-digit country code

AREA_AFF - Geographic area affected by disease

DT_START - Date health event started

DT_END - Date health event ended

TYPE - Type of disease group

DISEASE - Name of disease

NUM_DTH - Number of people reported dead from disease

NUM_AFF - Number of people affected from disease

SOURCE_DT - Source creation date

SOURCE - Primary source

Collection

This HGIS was created using information collected from several websites. EM-DAT, the World Health Organization, and news reports provided information about the outbreaks.

The data included herein have not been derived from a registered survey and should be considered approximate unless otherwise defined. While rigorous steps have been taken to ensure the quality of each dataset, DigitalGlobe Analytics is not responsible for the accuracy and completeness of data compiled from outside sources.

Sources (HGIS)

Egunganga, Vincent, Ami Sadiq, and Hir Joseph. All AfricaHIR JOSEPH, "Nigeria: Lassa Fever Returns Vicio." Last modified March 09, 2013. Accessed April 16, 2013. http://allafrica.com/.

EM DAT, "Country Database; Nigeria." Last modified March 2013. Accessed April 16, 2013. http://www.emdat.be/.

World Health Organization, "Global Health Observatory; Nigeria." Last modified 2012. Accessed April 16, 2013. http://www.who.int/en/.

Sources (Metadata)

Encyclopedia of the Nations, "Nigeria Country Specific Information." Last modified 2013. Accessed March 28, 2013. http://www.nationsencyclopedia.com.

Kates, Jennifer, and Alyssa Wilson Leggoe. The Henry J. Kaiser Family Foundation, "HIV/AIDS; The HIV/AIDS Epidemic in Nigeria." Last modified October 2005. Accessed April 16, 2013. http://www.kff.org/.

United States Embassy in Nigeria, "Nigeria Malaria Fact Sheet." Last modified December 2011. Accessed April 16, 2013. http://nigeria.usembassy.gov.

World Health Organization, "Global Task Force on Cholera Control." Last modified January 18, 2012. Accessed April 16, 2013. http://www.who.int/.

World Health Organization, "Meningococcal disease: situation in the African Meningitis Belt." Last modified 2012. Accessed March 14, 2013. http://www.who.int/csr/don/2012_05_24/en/index.html.

This statistic shows the estimated number of Muslims living in different European countries as of 2016. Approximately **** million Muslims were estimated to live in France, the most of any country listed. Germany and the United Kingdom also have large muslim populations with **** million and **** million respectively.

The aim of the EURISLAM research project is to provide a systematic analysis of cross-national differences and similarities in countries’ approaches to the cultural integration of immigrants in general and Muslims in particular. The countries studied in the research project are Belgium, France, Germany, The Netherlands, Switzerland and the United Kingdom. The core research question can be formulated as follows: ‘How have different traditions of national identity, citizenship and church-state relations affected European immigration countries’ incorporation of Islam, and what are the consequences of these approaches for patterns of cultural distance and interaction between Muslim immigrants and their descendants, and the receiving society?’ In order to answer this question, policy differences are related to cross-national variation in cultural distance and interaction between Muslims and the receiving society population. Three more specific research questions have been designed which are the focus in 7 different Work packages of the EURISLAM research project. The different methodologies used in the Work packages are later combined in the research project, allowing for a triangulation of research findings and a combination of quantitative and qualitative insights.In Work package 3 of the EURISLAM project a survey questionnaire has been developed which enabled a study of the individual characteristics of Muslim immigrants. This survey is designed to answer one of the three specific research questions used in this project: ‘To what extent do we find differences across immigration countries in cultural distance and patterns of interaction between various Muslim immigrant groups and the receiving society population?’ On the one hand, we focussed on attitudes, norms, and values, particularly those relating to democratic norms, gender relations and family values, ethnic, religious, and receiving society identification, and attitudes towards relations across ethnic and religious boundaries. On the other hand, the study looked at cultural and religious resources and practices, such as language proficiency, adherence to various religious practices (e.g., attendance of religious services or wearing of a headscarf), interethnic and interreligious partnerships and marriages, the frequency and quality of interethnic and interreligious relationships with neighbours, friends, and colleagues, and memberships in social and political organisations of the own ethnic and religious group as well as of the receiving society. Both types of questions have been asked – of course where relevant in an adapted format – with regard to members of the dominant ethnic group of the receiving society, because, obviously, cultural distance and interactions are determined by the perceptions, attitude, and practices at both ends of the relationship. All these variables were gathered by way of a survey in each of the countries of a number of selected Muslim immigrant groups, as well as a sample of receiving society ethnics. The data of this survey is now published together with a Codebook.In the revised edition of the codebook new information is added on the religion group variables in Block 3. In retrospect ambiguity appeared in the survey questionnaire specifically in the religion questions which (may) imply missing values for respondents of the ‘Atheist/agnostic/Do not belong to any denomination’ religious faith denomination group. These missing values may lead to distortions when using variables of the religion group. More details on this issue can be found on page 16 (3.2 Information on religion variables) of the revised codebook.Specific information on the project duration has been added on page 8 (1.3 Project Duration) of the revised codebook.The EURISLAM Dataset Survey-data published on October 6, 2015 has not been revised.

In 2020, around **** percent of the Iranian population identified as Muslim. Around ** percent identified as Shia Muslims in the same year, while a much smaller share followed the Sunni Muslim religion. In Iran, most Sunni Muslims belong to ethnic minority groups. Iran’s demographics The total population in Iran has grown steadily and is expected to surpass ** million in 2028. The vast majority of the population in the country was between 15 and 64 years of age. At the same time, the share of people aged above 64 increased in recent years and constituted over ***** percent of the total population. Muslim population worldwide In Europe, it was estimated that the Muslim population could triple by the middle of the century. In Southeast Asia, Indonesia had the largest share of Muslims as a proportion of its population. On the African continent, the highest number of Muslims was estimated in Nigeria, with close to a hundred million Islam followers. In the United States, less than one percent of the population identified as Muslims.

The North American Halal food and beverage market, currently valued at approximately $XX million (estimated based on available data and market trends in similar regions), is projected to experience robust growth, exhibiting a Compound Annual Growth Rate (CAGR) of 3.50% from 2025 to 2033. This expansion is fueled by several key drivers. The rising Muslim population in North America, coupled with a growing awareness and acceptance of Halal products among non-Muslim consumers seeking healthier and ethically sourced food options, significantly contributes to market growth. Increasing disposable incomes and a shift towards convenient and ready-to-eat meals further boost demand. Specific product categories like Halal meat, bakery items, and confectionery are experiencing particularly strong growth due to their cultural significance and established consumer base. The distribution network continues to evolve, with supermarkets and hypermarkets representing the largest sales channel, complemented by the increasing prominence of online retailers and specialty stores catering to niche Halal product needs. However, challenges remain, including the need for stricter regulatory frameworks and standardized Halal certification processes to ensure consumer trust and confidence. Furthermore, price competitiveness and the potential for supply chain disruptions could pose challenges to sustained market growth. The segmentation of the market reveals significant opportunities. The United States holds the largest market share within North America, followed by Canada and Mexico. Key players like Nestle S.A., Saffron Road, and American Foods Group LLC are actively shaping market dynamics through product innovation, brand building, and strategic partnerships. The forecast period of 2025-2033 presents a significant window for growth, driven by ongoing trends like increasing health consciousness, demand for ethically sourced products, and the rise of online food delivery platforms catering to diverse dietary preferences. This market demonstrates considerable potential for both established players and new entrants, necessitating a strategic approach that balances product diversification, market penetration, and effective brand positioning to capitalize on the expanding consumer base. Recent developments include: January 2022: Cresent Foods launched its halal-certified products in the H.E.B Stores located across Houston, United States. The products include a variety of fresh, halal hand-cut chicken, beef, and lamb products., November 2021: Cresent Foods partnered with Costco Business Center, Walmart, and Kroger stores located across the United States. The stores offer single whole turkeys and other meat products in fresh and frozen formats., May 2021: Health Mother and Health Baby Organization launched a halal-certified United Nations International Multiple Micronutrient Antenatal Preparation Multiple Micronutrient Supplements (UNIMMAP MMS) in the United States. According to the company, the supplements contain 15 vitamins and minerals, including iron and folic acid, in recommended dosages for women and are also cost-effective.. Notable trends are: Halal Certification Attracting a New Consumer Base.

In the 3 years to March 2021, white British families were the most likely to receive a type of state support.

IndQNER

IndQNER is a Named Entity Recognition (NER) benchmark dataset that was created by manually annotating 8 chapters in the Indonesian translation of the Quran. The annotation was performed using a web-based text annotation tool, Tagtog, and the BIO (Beginning-Inside-Outside) tagging format. The dataset contains:

3117 sentences

62027 tokens

2475 named entities

18 named entity categories

Named Entity Classes

The named entity classes were initially defined by analyzing the existing Quran concepts ontology. The initial classes were updated based on the information acquired during the annotation process. Finally, there are 20 classes, as follows:

Allah

Allah's Throne

Artifact

Astronomical body

Event

False deity

Holy book

Language

Angel

Person

Messenger

Prophet

Sentient

Afterlife location

Geographical location

Color

Religion

Food

Fruit

The book of Allah

Annotation Stage

There were eight annotators who contributed to the annotation process. They were informatics engineering students at the State Islamic University Syarif Hidayatullah Jakarta.

Anggita Maharani Gumay Putri

Muhammad Destamal Junas

Naufaldi Hafidhigbal

Nur Kholis Azzam Ubaidillah

Puspitasari

Septiany Nur Anggita

Wilda Nurjannah

William Santoso

Verification Stage

We found many named entity and class candidates during the annotation stage. To verify the candidates, we consulted Quran and Tafseer (content) experts who are lecturers at Quran and Tafseer Department at the State Islamic University Syarif Hidayatullah Jakarta.

Dr. Eva Nugraha, M.Ag.

Dr. Jauhar Azizy, MA

Dr. Lilik Ummi Kultsum, MA

Evaluation

We evaluated the annotation quality of IndQNER by performing experiments in two settings: supervised learning (BiLSTM+CRF) and transfer learning (IndoBERT fine-tuning).

Supervised Learning Setting

The implementation of BiLSTM and CRF utilized IndoBERT to provide word embeddings. All experiments used a batch size of 16. These are the results:

Maximum sequence length Number of e-poch Precision Recall F1 score

256 10 0.94 0.92 0.93

256 20 0.99 0.97 0.98

256 40 0.96 0.96 0.96

256 100 0.97 0.96 0.96

512 10 0.92 0.92 0.92

512 20 0.96 0.95 0.96

512 40 0.97 0.95 0.96

512 100 0.97 0.95 0.96

Transfer Learning Setting

We performed several experiments with different parameters in IndoBERT fine-tuning. All experiments used a learning rate of 2e-5 and a batch size of 16. These are the results:

Maximum sequence length Number of e-poch Precision Recall F1 score

256 10 0.67 0.65 0.65

256 20 0.60 0.59 0.59

256 40 0.75 0.72 0.71

256 100 0.73 0.68 0.68

512 10 0.72 0.62 0.64

512 20 0.62 0.57 0.58

512 40 0.72 0.66 0.67

512 100 0.68 0.68 0.67

This dataset is also part of the NusaCrowd project which aims to collect Natural Language Processing (NLP) datasets for Indonesian and its local languages.

How to Cite

@InProceedings{10.1007/978-3-031-35320-8_12,author="Gusmita, Ria Hariand Firmansyah, Asep Fajarand Moussallem, Diegoand Ngonga Ngomo, Axel-Cyrille",editor="M{\'e}tais, Elisabethand Meziane, Faridand Sugumaran, Vijayanand Manning, Warrenand Reiff-Marganiec, Stephan",title="IndQNER: Named Entity Recognition Benchmark Dataset from the Indonesian Translation of the Quran",booktitle="Natural Language Processing and Information Systems",year="2023",publisher="Springer Nature Switzerland",address="Cham",pages="170--185",abstract="Indonesian is classified as underrepresented in the Natural Language Processing (NLP) field, despite being the tenth most spoken language in the world with 198 million speakers. The paucity of datasets is recognized as the main reason for the slow advancements in NLP research for underrepresented languages. Significant attempts were made in 2020 to address this drawback for Indonesian. The Indonesian Natural Language Understanding (IndoNLU) benchmark was introduced alongside IndoBERT pre-trained language model. The second benchmark, Indonesian Language Evaluation Montage (IndoLEM), was presented in the same year. These benchmarks support several tasks, including Named Entity Recognition (NER). However, all NER datasets are in the public domain and do not contain domain-specific datasets. To alleviate this drawback, we introduce IndQNER, a manually annotated NER benchmark dataset in the religious domain that adheres to a meticulously designed annotation guideline. Since Indonesia has the world's largest Muslim population, we build the dataset from the Indonesian translation of the Quran. The dataset includes 2475 named entities representing 18 different classes. To assess the annotation quality of IndQNER, we perform experiments with BiLSTM and CRF-based NER, as well as IndoBERT fine-tuning. The results reveal that the first model outperforms the second model achieving 0.98 F1 points. This outcome indicates that IndQNER may be an acceptable evaluation metric for Indonesian NER tasks in the aforementioned domain, widening the research's domain range.",isbn="978-3-031-35320-8"}

Contact

If you have any questions or feedback, feel free to contact us at ria.hari.gusmita@uni-paderborn.de or ria.gusmita@uinjkt.ac.id