We are a subdivision of the Department of Computer Science at the University of Innsbruck.
Our passion lies in developing innovative methods for efficient data storage and analyses aiming to assist users and businesses to meet their information needs.
Team RecSys will have a busy week at the ACM Recommender Systems Conference 2023 in Singapore: on Monday, Amir (paper) and Andreas (paper) will present their works in the doctoral symposium. On Tuesday, Eva (together with Christine Bauer and Alan Said) will hold the third PERSPECTIVES workshop. On Friday, Andreas will present our paper "SPARE: Shortest Path Global Item Relations for Efficient Session-based Recommendation". Furthermore, Eva and Christine Bauer will present "Evaluating Recommender Systems: Survey and Framework" (paper), published in ACM Computing Surveys, for which they received the Women in RecSys Journal Paper of the Year award (senior category).
We are thrilled to announce that two Doctoral Symposium papers have been accepted for presentation at the prestigious RecSys 2023 Conference in Singapore during September 2023. One paper, authored by Andreas Peintner, plans to contribute significantly to advancing Graph-based Sequential Recommender Systems. The second accepted paper, authored by Amir Reza Mohammadi, promises to make valuable contributions to the development of Explainable Graph Neural Network Recommenders. These notable contributions hold the potential to shape the future of Recommender Systems.
We are very proud that our paper "SPARE: Shortest Path Global Item Relations for Efficient Session-based Recommendation" has just been accepted as a long paper at the ACM Conference on Recommender Systems (RecSys) 2023 in Singapore. In this paper, we propose to model the multi-hop information aggregation mechanism of GNNs over multiple layers via shortest-path edges based on knowledge from the sequential recommendation domain. Additionally, we apply supervised contrastive learning to address the inherent data sparsity.
Eva held a keynote at the Workshop on Machine Learning for Streaming Media at the Web Conference 2023 in Austin. The title of the talk was “What Can We Learn From Analyzing Streaming Music Data?”, detailing the potential of public streaming datasets, example case studies, but also caveats and limitations of using such datasets for research.
Our report on the 2nd Workshop on the Perspectives on the Evaluation of Recommender Systems (PERSPECTIVES 2022) at RecSys 2022 has been published in the December issue of SIGIR Forum.
Last week, Marta Moscati presented our paper "Music4All-Onion -- A Large-Scale Multi-Faceted Content-Centric Music Recommendation Dataset" at the 31st ACM International Conference on Information & Knowledge Management conference. The paper is available here and the dataset and code is publicly available here. This research is part of our FWF project "Humans and Recommender Systems - Towards a Mutual Understanding" (see https://humrec.github.io/ for further information).
This week, the 16th ACM Conference on Recommender Systems takes place and DBIS is part of it :)
We are very proud that our paper "Evaluating Recommender Systems: Survey and Framework" has just been accepted for publication at ACM Computing Surveys (impact factor 14.324). In this survey paper, Eva and Christine Bauer (Utrecht University) systematically review recommender system evaluation and introduce the “Framework for EValuating Recommender systems” (FEVR) that allows to categorize the evaluation space of recommender systems evaluation. The paper is already available via https://dl.acm.org/doi/10.1145/3556536.
Recently, a paper that Max, Eva and Günther authored together with Stefan Brandl and Markus Schedl of the Johannes Kepler Universität Linz was accepted for publication at the ISMIR 2022 conference. The paper is titled Verse Versus Chorus: Structure-aware Feature Extraction for Lyrics-based Genre Recognition, and investigates how the predictive power of lyrical features is impacted by which part of a song they are extracted from.
We look forward to presenting our work at ISMIR 2022 in December!
Together with Christine Bauer (Utrecht University) and Alan Said (University of Gothenburg), Eva will co-organize the 2nd Workshop on Perspectives on the Evaluation of Recommender Systems at this year's ACM Recommender Systems Conference.
Our manuscript on HOT (Height Optimized Tries) has now been published in ACM Transactions on Database Systems (ranked A*). In this article, we present an extended version of our previous SIGMOD paper on HOT - a fast and space-efficient in-memory index structure.
This week our our submission "HSP Datasets: Insights on Song Popularity Prediction" has been accepted for the IJSC special issue on IEEE ISM 2021.
Our IJSC journal paper is an extension of our paper "Novel Datasets for Evaluating Song Popularity Prediction Tasks" accepted at the ISM 2021. We extended our publication by providing further experiments and results. This extension is in three directions. First, we now include experiments utilizing Essentia’s mel-band features contained in our dataset. Second, we now additionally include experiments using the Essentia features computed on the short audio samples. Lastly, we extended the number of models used per data source and feature set. We now include a k-nearest neighbor approach for spectral-based features and extend the number of models utilized for predictions based on Mel-spectrograms. Doing so increased the total number of experiments where we report results from 96 to 330.
This also results in a fully reworked Results and Discussion section. We now show how to utilize our results (and subsets of them) to answer a diverse set of research questions regarding song popularity prediction. Based on our baselines, we discuss the best model per feature type. Further, we elaborate on the best hit song prediction approach among the included baseline models. In addition, we shed light on the question if all included measures of popularity are equally hard to predict and finally, we discuss if features extracted from the short audio samples have equal predictive power to those gathered from AcousticBrainz.
Last week, a dataset paper authored by DBIS members has been accepted at the ISM 2021:
The paper "Novel Datasets for Evaluating Song Popularity Prediction Tasks" authored by Michael Vötter, Maximilian Mayerl, Günther Specht, and Eva Zangerle has been accepted at the 23rd IEEE International Symposium on Multimedia (ISM 2021). In this paper, we present two novel datasets that can be utilized for hit song prediction tasks. For further details on the datasets, see: https://doi.org/10.5281/zenodo.5383858
This week, we welcome a new DBIS member: Andreas Peintner. Andreas will work as a PhD student in the field of recommender systems, particularly working on our HumRec project.
It's a busy week for DBIS: on Wednesday and Thursday, the results of the PAN challenges are presented at the CLEF conference (Conference and Labs of the Evaluation Forum). Maximilian and Eva have co-organized the Style Change Detection task as part of PAN (together with Martin Potthast and Benno Stein), Eva will present the task and the participant's results and approaches on Thursday. Find an overview and participant's papers as part of the proceedings on ceur-ws.
On Saturday, the Perspectives on the Evaluation of Recommender Systems Workshop (co-located with ACM Recommender Systems 2021) will take place. Eva is co-organizing this workshop together with Christine Bauer (Utrecht University) and Alan Said (Gothenburg University). Find the program, teaser videos for the papers and further information on the workshop website. We published the workshop proceedings on ceur-ws.
