Science Explorer Back to mapMap
Discussion
Topic · Artificial Intelligence

Sentiment Analysis and Opinion Mining

Sentiment Analysis and Opinion Mining is a research topic within Artificial Intelligence. Science Explorer counts 26k research works in it since 1970. 9.8% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on sentiment analysis and opinion mining, particularly in the context of social media and text mining. It covers various techniques such as lexicon-based methods, deep learning, aspect-based sentiment analysis, and machine learning for analyzing emotions and opinions in textual data from platforms like Twitter. The research also delves into emotion recognition and the impact of sentiment analysis on public perception.

  • Sentiment Analysis
  • Opinion Mining
  • Social Media
  • Text Mining
  • Emotion Recognition
  • Deep Learning
  • Aspect-based Sentiment Analysis
  • Lexicon-Based Methods
  • Twitter Sentiment
  • Machine Learning
Research works
26k
fractional, since 1970
In the world top 10%
2.5k
per year above
Top-10% rate
9.8%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+75%
the tick is no change
Largest producer
China
33% of the 10 largest, 2022-now
Sentiment Analysis and Opinion Mining

Which countries lead Sentiment Analysis and Opinion Mining research?

By volume, China and India publish the most (3.2k and 3k works in 2022-now).

By volume, 2022-now

  1. 1 China 3.2k works
  2. 2 India 3k works
  3. 3 Indonesia 1k works
  4. 4 United States 994 works
  5. 5 United Kingdom 270 works
  6. 6 Bangladesh 266 works
  7. 7 Türkiye 258 works
  8. 8 Malaysia 245 works
  9. 9 Saudi Arabia 223 works
  10. 10 ?? 214 works

How concentrated that is

The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.

China: 33.1%India: 31.0%Indonesia: 10.7%United States: 10.2%6 others listed: 15.1%33%largest
China3,234 · 33.1%India3,033 · 31.0%Indonesia1,047 · 10.7%United States994 · 10.2%6 others listed1,475 · 15.1%

Shares of the rows listed above, not of the whole node.

Which institutions lead Sentiment Analysis and Opinion Mining research?

By volume in 2022-now, Binus University publishes the most Sentiment Analysis and Opinion Mining research, followed by Telkom University and SRM Institute of Science and Technology.

By volume, 2022-now

  1. 1 Binus UniversityIndonesia 125 works
  2. 2 Telkom UniversityIndonesia 122 works
  3. 3 SRM Institute of Science and TechnologyIndia 103 works
  4. 4 Chinese Academy of SciencesChina 76 works
  5. 5 Amrita Vishwa VidyapeethamIndia 75 works
  6. 6 Vellore Institute of Technology UniversityIndia 73 works
  7. 7 Chandigarh UniversityIndia 68 works
  8. 8 Delhi Technological UniversityIndia 53 works
  9. 9 Saveetha UniversityIndia 50 works
  10. 10 Harbin Institute of TechnologyChina 48 works

Who are the leading researchers in Sentiment Analysis and Opinion Mining?

The most-cited researchers publishing on Sentiment Analysis and Opinion Mining include Yoshua Bengio, Kai You Wang and Lei Jiang.

  1. 1 Yoshua Bengio Canada 476k citations
  2. 2 Kai You Wang China 224k citations
  3. 3 Lei Jiang China 214k citations
  4. 4 Zahid A Butt Canada 198k citations
  5. 5 Paul M. Thompson United States 196k citations
  6. 6 Christopher D. Manning United States 179k citations
  7. 7 Han Zhang China 161k citations
  8. 8 Carlos Manuel Duarte Saudi Arabia 152k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

What are the most cited papers in Sentiment Analysis and Opinion Mining?

The most cited paper in Sentiment Analysis and Opinion Mining is "Convolutional Neural Networks for Sentence Classification" (Yoon Kim, 2014), with 14,059 citations. Next come "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks" (12,029) and "Mining and summarizing customer reviews" (7,770).

Most cited papers
#PaperReleasedCitations
1 Convolutional Neural Networks for Sentence Classification Yoon Kim Conference paperOpen access 2014 14,059
2 Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Nils Reimers, Iryna Gurevych Conference paperOpen access 2019 12,029
3 Mining and summarizing customer reviews Minqing Hu, Bing Liu Conference paper 22 Aug 2004 7,770
4 Thumbs up? Bo Pang, Lillian Lee, Shivakumar Vaithyanathan Conference paperOpen access 2002 7,061
5 Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank Richard Socher, Alex Perelygin, Jean Y. Wu et al. Conference paperOpen access 2013 6,886
All 99 most cited papers, with filters and sorting

Where is Sentiment Analysis and Opinion Mining research done?

The largest centres of Sentiment Analysis and Opinion Mining research in 2022-now are Beijing (China), Chennai (India), Jakarta (Indonesia) and Shanghai (China). Among places with at least 20 works in it, it is an unusually large share of all research in Faridabad, Chittagong and Vijayawada.

Largest cities, 2022-now

  1. 1 BeijingChina 517 works
  2. 2 ChennaiIndia 297 works
  3. 3 JakartaIndonesia 217 works
  4. 4 ShanghaiChina 200 works
  5. 5 BandungIndonesia 186 works
  6. 6 BengaluruIndia 172 works
  7. 7 DhakaBangladesh 168 works
  8. 8 GuangzhouChina 168 works
  9. 9 WuhanChina 160 works
  10. 10 New DelhiIndia 160 works

Where it is the local speciality

  1. FaridabadIN · 29.0 works11×
  2. ChittagongBD · 49.9 works11×
  3. VijayawadaIN · 62.1 works11×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Sentiment Analysis and Opinion Mining than the world average.

See Sentiment Analysis and Opinion Mining on the map

Where is the best place to study Sentiment Analysis and Opinion Mining?

Among universities, judged by research, Nanyang Technological University, Harbin Institute of Technology and Hong Kong Polytechnic University score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%20%40%mean 26.05%fractional works in this field (log) →share of work in the world top 10% →Hong Kong Polytechni…Nanyang Technologica…Harbin Institute of …King Abdulaziz Unive…
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1Nanyang Technological UniversitySingapore 71.325.5%3.4×31 +13.3%
2Harbin Institute of TechnologyChina 66.624.2%2.6×48 +54.7%
3Hong Kong Polytechnic UniversityChina 63.526.4%2.5×24 +13.7%
4King Abdulaziz UniversitySaudi Arabia 63.217.8%4.8×30 +90.1%
5National University of SingaporeSingapore 63.124.0%1.4×19 +43.4%
6Fudan UniversityChina 61.632.5%1.0×18 +57.2%
7Gachon UniversitySouth Korea 60.727.6%3.2×9 +541.2%
8Sun Yat-sen UniversityChina 60.130.1%0.9×22 +7.7%
9Wuhan UniversityChina 59.420.4%2.3×37 +50.5%
10Guangxi Normal UniversityChina 58.432.0%4.2×10 +116.3%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Sentiment Analysis and Opinion Mining, country by country

Is Sentiment Analysis and Opinion Mining research growing?

Output in 2022-2025 was 75% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Sentiment Analysis and Opinion Mining.

still counting19801990200020102020
grewheldshrank

The same series as a ribbon: one cell per year, darker for more. The line above answers how much; this answers when.

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Sentiment Analysis and Opinion Mining as a percentage of every work published that year, 0.053% in 2024.

still counting0.025%0.050%0.075%Sentiment Analysis and Opinion Mining0.062% in 202519801990200020102020

Fractional works of Sentiment Analysis and Opinion Mining over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Sentiment Analysis and Opinion Mining9.8% in 202520102020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

Which topics inside it are moving

Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.

Discussion

Ask a question or share a note about Sentiment Analysis and Opinion Mining. Posts are plain text and can be reported.