AMiner - AI Empowered Technology Intelligence Mining - Academic Search - Paper Retrieval - Paper Patent - Literature Tracking - Scholar Profile

AMiner was established by the Department of Computer Science and Technology at Tsinghua University, which includes over 320 million academic papers/patents and a technology map of 133 million scholars. It provides scientific and technological intelligence services such as academic search, paper search, recommended subscriptions, paper patents, scholar portraits, literature tracking, trend analysis, etc. It is an academic and technological intelligence big data mining and service system platform with completely independent intellectual property rights in China.

AMiner (aminar. org) aims to provide comprehensive search and mining services for researchers on social networks. In this system, our focus is on: (1) creating a semantic based archive for each researcher by extracting information from the distributed network; (2) Integrate academic data from multiple sources (such as bibliographic data and researcher profiles); (3) Accurately search heterogeneous networks; (4) Analyze and discover interesting patterns from established researcher social networks. The main search and analysis functions in AMiner include:

Overview search: Enter the researcher's name (e.g. Tang Jie), and the system will return a semantic based overview created for the researcher using information extraction techniques. On the personal profile page, the extracted and integrated information includes: contact information, photos, citation statistics, academic achievement evaluation, (tense) research interests, educational history, personal social graph, research funding (currently only available in US and CN), publication records (including citation information, papers automatically assigned to several different domains).

Experts have found that when entering a query (such as data mining), the system will return experts for that topic. In addition, the system will recommend top conferences and ranked papers on the topic. There are two ranking algorithms, VSM and ACT. The former is similar to traditional language models, while the latter is based on our Author Conference Topic (ACT) model. Users can also provide feedback on search results.

Conference analysis: Enter a conference name (e.g. KDD), and the system returns who is the most active researcher at the conference, as well as the top ranked papers.

Course search: Enter a query (such as data mining), and the system will tell you who is teaching courses related to the query.

Subgraph search: Enter a query (e.g. data mining), and the system first tells you which topics are relevant to the query (e.g. five topics "Data Mining", "XML Data", "Data Mining/Query Processing", "Web Data/Database Design", "Web Mining" are relevant), then displays the most important subgraphs found on each related topic and adds a summary of the subgraphs.

Theme Browser: Based on our Author Conference Theme (ACT) model, we automatically discover 200 popular topics from publications. For each topic, we will automatically assign a label to represent its meaning. Furthermore, the browser displays the most active researchers, the most relevant conferences/papers, and discovers the evolving trends of topics.

Academic ranking: We have defined 8 metrics to evaluate the achievements of researchers. The measurement criteria include "h-index", "citation", "upward trend", "activity level", "lifespan", "diversity", "social ability", and "rising star". For each metric, we output a ranking list for different domains. For example, you can search for who has the most citations in the field of "data mining".

User management: You can register as a user to: (1) modify extracted profile information; (2) Provide feedback on search results; (3) Track researchers in Miner; (4) Create an AMiner page (which can be used to promote confs/workshops or enrollment).

AMiner.org has been running on the Internet for more than three years. At present, the academic network includes over 6000 conferences, 3200000 publications, and 700000 researcher profiles. The system has attracted users from over 200 countries and receives more than 200000 access logs per day. The top five countries from which users come are the United States, China, Germany, India, and the United Kingdom.