Dr.-Ing. Max Zimmermann
Dr.-Ing. Max Zimmermann
- Aspect Based Opinion Mining & Sentiment Analysis
- Opinion Monitoring
- Predictive Sentiment Analysis
- Large Scale Data Analysis
- Semi-Supervised Stream Classification
- Stream Mining
- 2011/06 - 2014/12 [completed]: German Research Foundation project SP 572/11-1 "IMPRINT: Incremental Mining for Perennial Objects"
- 2011/10 - 2014/12 [completed]: Tracking people's perception of products over time with Opinion Stream Mining
- 2012/04 - 2013/04 [completed]: Job/Skill Crawler
- 2011/01 - 2012/12 [completed]: Recommendation Engines for the Web 2.0
- 2009/02 - 2009/09 [completed]: KO-RFID
- Stanford Twitter Sentiment Dataset
- Product Review Dataset: 9 Products; 38 Product Features.
- Product Review Dataset: 327 Product Features, roughly 13.000 Reviews
Does Tinnitus Depend on Time-of-Day? An Ecological Momentary Assessment Study with the ``TrackYourTinnitus'' Application. Frontiers in Aging Neuroscience, (9):253, 2017. URL
Ageing-Based Multinomial Naive Bayes Classifiers Over Opinionated Data Streams. In Annalisa Appice, Pedro Pereira Rodrigues, Vítor Santos Costa, Carlos Soares, João Gama, and Alípio Jorge (Eds.), Machine Learning and Knowledge Discovery in Databases, (9284):401-416, Springer International Publishing, 2015. URL
Discovering and Monitoring Product Features and the Opinions on them with OPINSTREAM. Neurocomput., (Volume 150)Part A:Pages 1-346, Elsevier Science Publishers B. V., Amsterdam, The Netherlands, The Netherlands, 2015.
Incremental Active Opinion Learning Over a Stream of Opinionated Documents. WISDOM'15 (Workshop on Issues of Sentiment Discovery and Opinion Mining) 2015 at Knowledge Discovery and Data Mining, KDD'15 Workshops 2015, Sydney, Australia, August 10, 2015, 2015.
Extracting opinionated (sub)features from a stream of product reviews using accumulated novelty and internal re-organization. Information Sciences, -, 2015. URL
Discovering and Monitoring Product Features and the Opinions on them with OPINSTREAM. Neurocomput., Elsevier Science Publishers B. V., Amsterdam, The Netherlands, The Netherlands, 2014.
Adaptive Semi Supervised Opinion Classifier With Forgetting Mechanism. Proc. of the 29th Annual ACM Symposium on Applied Computing, ACM, 2014.
A Semi-supervised Self-Adaptive Classifier over Opinionated Streams. Proceedings of the 2014 IEEE 14th International Conference on Data Mining Workshops, IEEE Computer Society, Washington, DC, USA, 2014.
Extracting Opinionated (Sub)Features from a Stream of Product Reviews. In Johannes Fürnkranz, Eyke Hüllermeier, and Tomoyuki Higuchi (Eds.), Discovery Science, (8140):340-355, Springer Berlin Heidelberg, 2013. URL
Discovering Global and Local Bursts in a Stream of News. Proceedings of the 27th Annual ACM Symposium on Applied Computing, 807--812, ACM, New York, NY, USA, 2012. URL
Finding Stops in Error-Prone Trajectories of Moving Objects with Time-Based Clustering. Intelligent Interactive Assistance and Mobile Multimedia Computing, (53):275-286, Springer Berlin Heidelberg, 2009.
- Summer term 2011,2012 & 2013: Exercise class "Data Mining"
- Winter term 2012: Lecturer "Advanced Topics in Knowledge Management and Discovery (Sentiment/Opinion Mining)"
- Summer term 2013&2014: Coordinating "Seminar Bachelor"
- ERASMUS Teachers’ Mobility Program: Short lecture on "Advances in Opinion Stream Mining", Mai 2014 @ University of Thessaloniki, Greece
- Invited Talk: "Burst detection in streams of news data", September 2011@ University of Thessaloniki, Greece
- Bachelor Theses
- Steven Böhlert (2011):
- Classification on microblogging text while utilizing well known techniques from text mining
- Sebastian Schultz (2012) in cooperation with Fraunhofer Institute for Factory Operation and Automation:
- Conception and design of a tool for hypothesis test upon databases
- Friedrich Lüder (2012) in cooperation with fme AG:
- Implementation of a mobile application for multi-platforms to consuming information on the basis of HTML5 and PhoneGap
- Matthias Lange (2013) in cooperation with Advanto Software GmbH:
- Predicting interest and trends of fiscal data at federal level
- Christian Bischoff (2013) in cooperation with Otto-von Guericke University of Magdeburg:
- Exploiting opinion mining for customer relationship management systems
- Jan Düwel (2013) in cooperation with Otto-von Guericke University of Magdeburg:
- Dynamic feature spaces in opinion stream classification
- Master Theses
- Alexander Kusz (2013) in cooperation with Otto-von Guericke University of Magdeburg:
- Sentiment analysis on product reviews by means of feature extraction and opinion summarization
- Tommy Hielscher (2013) in cooperation with Otto-von Guericke University of Magdeburg:
- Learn an adaptive domain specific lexion to compute the polarity of words
Advised Student Team/Software Projects (Software on request)
- Amazon Review Crawler (2011)
- Web crawler for job advertisements (2012)
- Skill predictor on evolving job advertisements (2013)
- Clustering of Opinionated Documents: A self-organizing map approach (2012)
- Learning Domain specific Lexicon (2013)
- Sentiment Visualization (2013)
- Efficient Unsupervised Discovery of Word Categories (2013)
- Efficiency of Density Based Hierachical Clustering in Opinion Mining (2014)
- Learning a polarity lexicon by WordNet Synonyms: A graph clustering approach (2014)