• A deep network model for paraphrase detection in short text messages 

      Agarwal, Basant; Ramampiaro, Heri; Langseth, Helge; Ruocco, Massimiliano (Journal article; Peer reviewed, 2018)
      This paper is concerned with paraphrase detection, i.e., identifying sentences that are semantically identical. The ability to detect similar sentences written in natural language is crucial for several applications, such ...
    • Applying temporal dependence to detect changes in streaming data 

      Duong, Quang-Huy; Ramampiaro, Heri; Nørvåg, Kjetil (Journal article; Peer reviewed, 2018)
      Detection of changes in streaming data is an important mining task, with a wide range of real-life ap- plications. Numerous algorithms have been proposed to efficiently detect changes in streaming data. However, the ...
    • Bayesian Text Categorization 

      Næss, Arild Brandrud (Master thesis, 2007)
      Natural language processing is an interdisciplinary field of research which studies the problems and possibilities of automated generation and understanding of natural human languages. Text categorization is a central ...
    • Effective hate-speech detection in Twitter data using recurrent neural networks 

      Pitsilis, Georgios; Ramampiaro, Heri; Langseth, Helge (Journal article; Peer reviewed, 2018)
      This paper addresses the important problem of discerning hateful content in social media. We propose a detection scheme that is an ensemble of Recurrent Neural Network (RNN) classifiers, and it incorporates various features ...
    • Explaining deep learning methods for recommender systems 

      Bjørgen, Erik; Hambro, Carl Johan (Master thesis, 2019)
      Systemkrav for anbefalingssystemer er i stadig endring. Formatet til anbefalinger, samt GDPR, har bragt med seg nye krav for anbefalingene som blir gitt. Forklarbarhet eller tolkbarhet er ett av disse nye kravene. orklarbarhet ...
    • Explaining deep learning methods for recommender systems 

      Bjørgen, Erik; Hambro, Carl Johan (Master thesis, 2019)
      Systemkrav for anbefalingssystemer er i stadig endring. Formatet til anbefalinger, samt GDPR, har bragt med seg nye krav for anbefalingene som blir gitt. Forklarbarhet eller tolkbarhet er ett av disse nye kravene. Forklarbarhet ...
    • Extracting news events from microblogs 

      Øystein, Repp; Ramampiaro, Heri (Journal article; Peer reviewed, 2018)
      Twitter stream has become a large source of information, but the magnitude of tweets posted and the noisy nature of its content makes harvesting of knowledge from Twitter has challenged researchers for long time. Aiming ...
    • Forecasting Intra-Hour Imbalances in Electric Power Systems 

      Saleh Salem, Tárik; Kathuria, Karan; Ramampiaro, Heri; Langseth, Helge (Journal article; Peer reviewed, 2019)
      Keeping the electricity production in balance with the actual demand is becoming a difficult and expensive task in spite of an involvement of experienced human operators. This is due to the increasing complexity of the ...
    • High Utility Drift Detection in Quantitative Data Streams 

      Duong, Quang-Huy; Ramampiaro, Heri; Nørvåg, Kjetil; Fournier-Viger, Philippe; Dam, Thu-Lan (Journal article; Peer reviewed, 2018)
      This paper presents an efficient algorithm for detecting changes (drifts) in the utility distributions of patterns, named High Utility Drift Detection in Transactional Data Stream (HUDD-TDS). The algorithm is specifically ...
    • Highly Efficient Pattern Mining Based on Transaction Decomposition 

      Djenouri, Youcef; Lin, Jerry Chun-Wei; Nørvåg, Kjetil; Ramampiaro, Heri (Chapter; Peer reviewed, 2019)
      This paper introduces a highly efficient pattern mining technique called Clustering-Based Pattern Mining (CBPM). This technique discovers relevant patterns by studying the correlation between transactions in transaction ...
    • Locality-adapted kernel densities of term co-occurrences for location prediction of tweets 

      Özdikis, Özer; Ramampiaro, Heri; Nørvåg, Kjetil (Journal article; Peer reviewed, 2019)
      While geographical metadata referring to the originating locations of tweets provides valuable information to perform effective spatial analysis in social networks, scarcity of such geotagged tweets imposes limitations on ...
    • Location prediction using neural networks 

      Løkken, Erlend; Waatevik, Endre (Master thesis, 2019)
      For å kunne studere brukeres bevegelser og handlinger er det viktig å identifisere lokasjonen en tweet er skrevet fra eller omhandler. Denne typen informasjon kan brukes i en rekke applikasjoner som avhenger av geografisk ...
    • New Insights into Content Production in Social Platforms 

      Kusmierczyk, Tomasz (Doctoral theses at NTNU;2018:173, Doctoral thesis, 2018)
      Social media influences to a great extent everyday life of millions of people, and therefore the understanding of certain patterns relating to online platforms and communities, and the ability to model and predict them, ...
    • Prediction Intervals: Split Normal Mixture from Quality-Driven Deep Ensembles 

      Saleh Salem, Tárik; Langseth, Helge; Ramampiaro, Heri (Peer reviewed; Journal article, 2020)
      Prediction intervals are a machine- and human-interpretable way to represent predictive uncertainty in a regression analysis. In this paper, we present a method for generating prediction intervals along with point estimates ...
    • Ranking Streaming Data With Continuous Queries 

      Skarshaug, Sandra Marie (Master thesis, 2019)
      En økende mengde data genereres som en del av digitaliseringen av samfunnet vårt. Forskning fra 2013 viser at 90% av all dataen generert i verden frem til det tidspunktet, ble generert i løpet av de to foregående årene. ...
    • Semantic Matching: Dynamic Composition of Matcher Ensembles for Ontology Alignment 

      Vennesland, Audun (Doctoral theses at NTNU;2020:247, Doctoral thesis, 2020)
      Semantic matching is a computational process that aims to automatically identify the semantic relationship between elements represented in different graph-like sources. Typically, this is a process that involves human ...
    • Sketching Streaming Histogram Elements using Multiple Weighted Factors 

      Duong, Quang-Huy; Ramampiaro, Heri; Nørvåg, Kjetil (Chapter, 2019)
      We propose a novel sketching approach for streaming data that, even with limited computing resources, enables processing high volume and high velocity data efficiently. Our approach accounts for the fact that a stream of ...
    • Space-time series clustering: Algorithms, taxonomy, and case study on urban smart cities 

      Belhadi, Asma; Djenouri, Youcef; Nørvåg, Kjetil; Ramampiaro, Heri; Masseglia, Florent; Lin, Jerry Chun-Wei (Journal article; Peer reviewed, 2020)
      This paper provides a short overview of space–time series clustering, which can be generally grouped into three main categories such as: hierarchical, partitioning-based, and overlapping clustering. The first hierarchical ...
    • Spatial Statistics of Term Co-occurrences for Location Prediction of Tweets 

      Özdikis, Özer; Ramampiaro, Heri; Nørvåg, Kjetil (Journal article; Peer reviewed, 2018)
      Predicting the locations of non-geotagged tweets is an active research area in geographical information retrieval. In this work, we propose a method to detect term co-occurrences in tweets that exhibit spatial clustering ...
    • Time Series Movement Data represented as 2D image: Prediction of CP with Pretrained autoencoder 

      Theisen, Mathilde; Wiik, Marie Ling (Master thesis, 2019)
      Denne masteroppgaven kartlegger hvordan tidsseriedata i form av koordinater kan representeres som bilder som både kan forstås av ikke-teknologiske klinikere og av en dyplæringsarkitektur, mer spesifikt en autoencoder. ...