This week, I have been attending the DEXA 2016 and DAWAK 2016 conferences, in Porto, Portugal, from the 4th to 8th September 2016, to present three papers. In this blog post, I will give a brief report about these conferences.
About these conferences
The DEXA conference is a well-established international conference related to database and expert systems. This year, it was the 27th edition of the conference. It is a conference that is held in Europe, every year, but still attracts a considerable amount of researchers from other continents.
DEXA is a kind of multi-conference. It actually consists of 6 small conferences that are organized together. Below, I provide a description of each of those sub-conferences and indicate their acceptance rate.
- DEXA 2016 (27th Intern. Conf. on Database and Expert Systems Applications).
Acceptance rate: 39 / 137 = 28% for full papers, and another 29 / 137 = 21 % for short papers
- DaWaK 2016 (18th Intern. Conf. on Big Data Analytics and Knowledge Discovery)
Acceptance rate: 25 / 73= 34%
- EGOVIS 2016 (5th Intern. Conf. on Electronic Government and the Information Systems Perspective)
Acceptance rate: not disclosed in the proceedings, 22 papers published
- ITBAM 2016 (7th Intern. Conf. on Information Technology in Bio- and Medical Informatics)
Acceptance rate: 9 / 26 = 36 % for full papers, and another 11 / 26 = 42% for short papers
- TrustBus 2016 (13th Intern. Conf. on Trust, Privacy, and Security in Digital Business)
Acceptance rate: 25 / 73= 43%
- EC-Web 2016 (17th Intern. Conf. on Electronic Commerce and Web Technologies)
Thus, the DEXA conference is more popular than DAWAK and the other sub-conferences and also is more competitive in terms of acceptance rate than the other sub-conferences.
The proceedings of each of the first five sub-conferences are published by Springer in the Lecture Notes in Computer Science Series, which is quite nice, as it ensures that the papers are indexed by major indexes in computer science such as DBLP. The proceedings of the conferences were given on a USB drive.
The conference location
The conference was locally organized by the Instituto Superior de Engenharia do Porto (ISEP) in Porto, Portugal. The location has been great, as Porto is a beautiful European city with a long history. The old town of Porto is especially beautiful. Moreover, visiting Porto is quite inexpensive.
First day of the conference
The first day of the conference started at 10:30 AM. The first day was mostly paper presentations. The main topics of the papers during the first day of DEXA were temporal databases, high-utility itemset mining, periodic pattern mining, privacy-preserving data mining, and clustering. In particular, I had two papers presentations related to itemsets mining:
- a paper presenting a new type of patterns called minimal high-utility itemsets
- a paper about discovering high utility itemsets with multiple thresholds.
Besides, there was a keynote entitled “From Natural Language to Automated Reasoning” by Bruno Buchberger from Austria, a famous researcher in the field of symbolic computation. The keynote was about using formal automated reasoners (e.g. math theorem prover) based on logic to analyze texts. For example, the speaker proposed to extract formal logic formulas from tweets to then understand their meaning using automated reasoners and a knowledge base provided by the user. This was a quite unusual perspective on tweet analysis since nowadays, researchers in natural language processing prefer using statistical approaches to analyze texts rather than using approaches relying on logic and a knowledge base. This gave rise to some discussion during the questions period after the keynote.
During the evening, there was also a reception in a garden inside the institute were the conference was held.
Second day of the conference
On the second day, I have attended DAWAK. In the morning, there was several paper presentations. I have presented a paper about recent high-utility itemset mining. The idea is to discover itemsets (set of items) that have been recently profitable in customer transactions, to then use this insight for marketing decisions. There was also an interesting paper presentation about big data itemset mining by student Martin Kirchgessner from France.
Then, there was an interesting keynote about the price of data by Gottfried Vossen from Germany. This talk started by discussing the fact that companies are collecting more and more rich data about persons. Usually, many persons give personal data for free to use services such as Facebook or Gmail. There also exist several marketplaces where companies can buy data such as the Microsoft Azure Marketplace and also different pricing models for data. For example, one could have different pricing models to sell more or less detailed views of the same data. There also exist repositories of public data. Moreover other issues are what happen with the data of someone when he dies. In the future, a new way of buying products could be to pay for data about the design of an object, and then print it by ourselves using 3d printers or other tools. Other issues related to the sale of data is DRM, selling second-hand data, etc. Overall, it was not a technical presentation, but it discussed an important topic nowadays which is the value of data in our society that relies more and more on technologies.
Third day of the conference
On the third day of the conference, there was more paper presentations and also a keynote that I have missed. On the evening, there was a nice banquet at a wine cellar named Taylor. We had the pleasure to visit the cellar, enjoy a nice dinner, and listen to a Portuguese band at the end of evening.
This was globally a very interesting conference. I had opportunity to discuss with some excellent researchers, especially from Europe, including some that I had met at other conferences. There was also some papers quite related to my sub-field of research in data mining. DEXA may not be a first tier conference, but it is a very decent conference, that I would submit more papers to in the future.
Philippe Fournier-Viger is a full professor and also the founder of the open-source data mining software SPMF, offering more than 110 data mining algorithms. If you like this blog, you can tweet about it and/or subscribe to my twitter account @philfv to get notified about new posts.