Jon Atle Gulla

Jon Atle Gulla
Norwegian University of Science and Technology | NTNU · Department of Computer and Information Science

PhD

About

137
Publications
20,571
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,654
Citations
Additional affiliations
August 2003 - present
Norwegian University of Science and Technology
Position
  • Professor (Full)

Publications

Publications (137)
Article
Political viewpoints identification (PVI) is a task in Natural Language Processing that takes political texts and recognizes the writer’s opinions towards a political matter. PVI reduces the ambiguity in texts by identifying the underlying meaning and clarifying the bias margin along the political spectrum (bias leaning). Thus, even non-experts can...
Chapter
We analyze the use of language models for political text classification. Political texts become increasingly available and language models have succeeded in various natural language processing tasks. We apply two baselines and different language models to data from the UK, Germany, and Norway. Observed accuracy shows language models improving on th...
Preprint
Full-text available
Open-domain conversational systems are assumed to generate equally good responses on multiple domains. Previous work achieved good performance on the single corpus, but training and evaluating on multiple corpora from different domains are less studied. This paper explores methods of generating relevant responses for each of multiple multi-domain c...
Article
The adoption of recommender systems in online news personalization has made it possible to tailor the news stream to the individual interests of each reader. Previous research on commercial recommender systems has emphasized their use in large-scale media houses and technology companies, and real-world experiments indicate substantial improvements...
Article
Entity matching is the problem of identifying which records refer to the same real-world entity. It has been actively researched for decades, and a variety of different approaches have been developed. Even today, it remains a challenging problem, and there is still generous room for improvement. In recent years, we have seen new methods based upon...
Article
With the dramatic expansion of international markets, consumers write reviews in different languages, which poses a new challenge for Recommender Systems (RSs) dealing with this increasing amount of multilingual information. Recent studies that leverage deep-learning techniques for review-aware RSs have demonstrated their effectiveness in modelling...
Preprint
Entity matching is the problem of identifying which records refer to the same real-world entity. It has been actively researched for decades, and a variety of different approaches have been developed. Even today, it remains a challenging problem, and there is still generous room for improvement. In recent years we have seen new methods based upon d...
Chapter
Full-text available
Datasets are an integral part of contemporary research on recommender systems. However, few datasets are available for conventional recommender systems and even very limited datasets are available when it comes to contextualized (time and location-dependent) News Recommender Systems. In this paper, we introduce an educational news dataset for recom...
Article
Full-text available
Online news recommendation aims to continuously select a pool of candidate articles that meet the temporal dynamics of user preferences. Most of the existing methods assume that all user-item interaction history are equally importance for recommendation, which is not alway applied in real-word scenario since the user-item interactions are sometime...
Conference Paper
Publishing news represents a vital function for societal health. News recommender systems, which support readers finding relevant content, face challenges beyond those encountered by other types of recommender systems. They have to deal with a dynamic flow of unstructured, fragmentary, and potentially unreliable news stories. The International Work...
Article
Explainable recommendation, which provides explanations about why an item is recommended, has attracted growing attention in both research and industry communities. However, most existing explainable recommendation methods cannot provide multi-model explanations consisting of both textual and visual modalities or adaptive explanations tailored for...
Article
Full-text available
Sammendrag Automatiserte anbefalinger av nyhetsinnhold brukes i dag på nettsidene til mange medieselskaper med hensikt å presentere leserne mer relevante nyheter og tilby bedre brukeropplevelser. Slike anbefalingsløsninger drar nytte av nye teknikker fra maskinlæring og stordataarkitekturer fra informatikkfaget. I denne artikkelen diskuterer vi om...
Article
Full-text available
The Editors-in-Chief have retracted “A joint model for analyzing topic and sentiment dynamics from large-scale online news” [1] because the article shows significant overlap with a previously published article [2] without proper citation.
Chapter
With the rapid proliferation of online social networks, personalized social recommendation has become an important means to help people discover useful information over time. However, the cold-start issue and the special properties of social networks, such as rich temporal dynamics, heterogeneous and complex structures with millions of nodes, rende...
Chapter
Despite the fact that recommender systems are becoming increasingly popular in every aspect of the web, users might hesitate to use these personalization-based services in return of their personal information if they believe their privacy is compromised in any possible way. While new privacy regulations in Europe bring more transparency and control...
Article
Full-text available
Textile production industry is one of the biggest industries available and it is known by its negative effects to the environment. Greenhouse gas emissions can drastically be reduced by just recycling the textile waste. Such textile recycling has become a lot easier with clothing retailers now starting to offer recycling checkpoints. Moreover, peop...
Conference Paper
Full-text available
The need for teaching realistic software development in project courses has increased in a global scale. It has always been challenges in cooperating fast-changing software technologies, development methodologies and teamwork. Moreover, such project courses need to be designed in the connection to existing theoretical courses. We performed a large-...
Preprint
Full-text available
The need for teaching realistic software development in project courses has increased in a global scale. It has always been challenges in cooperating fast-changing software technologies, development methodologies and teamwork. Moreover, such project courses need to be designed in the connection to existing theoretical courses. We performed a large-...
Conference Paper
Session-based recommendations have drawn more and more attention in many recommendation settings of modern online services. Unlike many other domains such as books and music, news recommendations suffer from new challenges of fast updating rate and recency issues of news articles and lack of user profiles. In this paper, we proposed a method that c...
Article
With the rapid proliferation of online social networks, personalized social recommendation has become an important means to help people discover their potential friends or interested items in real-time. However, the cold-start issue and the special properties of social networks, such as rich temporal dynamics, heterogeneous and complex structures,...
Chapter
Full-text available
Women have been shown to be effective leaders in many team-based situations. However, it is also well-recognized that women are underrepresented in engineering and technology areas, which leads to wasted efforts and a lack of diversity in professional organizations. Although studies about gender and leadership are rich, research focusing on enginee...
Chapter
Research on mobile news recommendation has become popular over the last few years, though the news domain is challenging and there are still few advanced commercial systems with success. This paper presents the exploratory news recommender system under development in the SmartMedia program. In exploratory news recommendation the reader can compose...
Conference Paper
Linked Open Data has proven useful in disambiguation and query extension tasks, but their incomplete and inconsistent nature may make them less useful in analyzing brief, low-level business transactions. In this paper, we investigate the effect of using Wikidata and DBpedia to aid in classification of real bank transactions. The experiments indicat...
Conference Paper
This project aims to explore to what extent external semantic resources on companies can be used to improve the accuracy of a real bank transaction classification system. The goal is to identify which implementations are best suited to exploit the additional company data retrieved from the Brønnøysund Registry and the Google Places API, and accurat...
Conference Paper
Datasets for recommender systems are few and often inadequate for the contextualized nature of news recommendation. News recommender systems are both time- and location-dependent, make use of implicit signals, and often include both collaborative and content-based components. In this paper we introduce the Adressa compact news dataset, which suppor...
Conference Paper
Time plays a crucial role in influencing and understanding users' changeable preferences among various factors which directly or indirectly result in users' interesting behavior. In this paper, we propose a neural time series forecasting model (NTSF) to fit and predict user preference trend according to time. In this model, we integrate emerging/ho...
Article
Many of today’s online news websites and aggregator apps have enabled users to publish their opinions without respect to time and place. Existing works on topic-based sentiment analysis of product reviews cannot be applied to online news directly because of the following two reasons: (1) The dynamic nature of news streams require the topic and sent...
Conference Paper
Full-text available
Decision-making in an emergency department needs to be efficient. It does not allow observation of the patient for a prolonged period of time, especially if the patients harm themselves or others, or refuses treatment. This includes suicidal, violent, intentional self-inflicted or non-consenting to treatments’ patient. Clinicians have to quickly de...
Article
Knowledge and information are valuable resources in enterprises for solution reuse. However, identifying relevant information from a rapidly growing number of unstructured resources is challenging for users. We discuss a personalized information access tool for professional workplaces based on recommender systems to provide relevant documents for u...
Conference Paper
Many of today’s online news websites and aggregator apps have enabled users to publish their opinions without respect to time and place. Existing works on topic-based sentiment analysis of product reviews cannot be applied to online news directly because of the following two reasons: (1) The dynamic nature of news streams require the topic and sent...
Conference Paper
Full-text available
Currently there are only limited data available on the habits and behaviour of pedestrians and cyclists towards private motor vehicles and public transport. The only data on cyclists’ behaviour originates from sparsely distributed counting points throughout Trondheim city in Norway. Current counting devices are few, unreliable and expensive to manu...
Article
Full-text available
The use of smartphones and tablets has increased significantly in the past years and changed the way we consume news. In this paper, we will describe a news stream aggregating system that automatically recognize and disambiguate geo spatial and meaning bearing entities in news text. The system utilizes the entity definitions and associations in Wik...
Article
User profiling is an important part of content-based and hybrid recommender systems. These profiles model users' interests and preferences and are used to assess an item's relevance to a particular user. In the news domain it is difficult to extract explicit signals from the users about their interests, and user profiling depends on in-depth analys...
Article
Recommender systems are built to provide the most proper item or information within the huge amount of data on the internet without the manual effort of the users. As a specific application domain, news recommender systems aim to give the most relevant news article recommendations to users according to their personal interests and preferences. News...
Article
Datasets are important for training and testing many information processing applications. In the field of news recommendation, there are still few available datasets, and many feel obliged to use nonnews datasets to test their algorithms for news recommendation. This paper presents some of the most common datasets for recommender systems in general...
Conference Paper
Full-text available
Recommending news articles entails additional requirements to recommender systems. Such requirements include special consumption patterns, fluctuating itemcollections, and highly sparse user profiles. This workshop (NRS'13@RecSys) brought together researchers and practitioners around the topics of designing and evaluating novel news recommender sys...
Conference Paper
Full-text available
Mobile news recommender systems help users retrieve news that is relevant in their particular context and can be presented in ways that require minimal user interaction. In spite of the availability of contextual information about mobile users, though, current mobile news applications employ rather simple strategies for news recommendation. Our mul...
Conference Paper
Social recommender systems aim to alleviate the information overload problem on social network sites. The social network structure is often an important input to these recommender systems. Typically, this structure cannot be inferred directly from declared relationships among users. The goal of our work is to extract an underlying hidden and sparse...
Article
Full-text available
In group recommendation systems, recommendations may be given to arbitrarily composed groups that may not display any particular characteristics across group members. Since individual recommendation systems can assume that the users' previous behavior is sufficient for coming up with new recommendations, statistical analyses of user logs or user pr...
Conference Paper
As more and more reviews are generated online, sentiment analysis has been widely studied and developed both in academia and industry recently. In this paper, we propose a novel approach to tackle two complementary sub-tasks of sentiment analysis on review texts, i.e., the Attribute Detection (AD) task and the Sentiment Orientation (SO) task, in a...
Article
Full-text available
Process mining relates to the extraction of non-trivial and useful information from information system event logs. It is a new research discipline that has evolved significantly since the early work on idealistic process logs. Over the last years, process mining prototypes have incorporated elements from semantics and data mining and targeted visua...
Article
Ontologies have been a hot research topic for the recent decade and have been used for many applications such as information integration, semantic search, knowledge management, etc. Manual engineering of ontologies is a costly process and automatic ontology engineering lacks in precision. Folksonomies have recently emerged as another hot research t...
Conference Paper
Full-text available
Folksonomies are becoming increasingly popular, both among users who find them simple and intuitive to use, and scientists as interesting research objects. Folksonomies can be viewed as large informal sources of semantics. Harnessing the semantics for search or concept extraction requires us to be able to recognize linguistic similarity between tag...
Conference Paper
Full-text available
Search has been and will continue to be an important tool for users who need to locate information in an ever increasing mount of resources. Not all queries have a well defined information need that can easily be described by a keyword query. Exploratory search is one such type of search where the user is not necessarily proficient in the domain or...
Conference Paper
Full-text available
Online news usually describes various events over multiple topics. Some of them may generate great impact and affection on other events, organizations or people. For example, a bankruptcy news about a big company may generate a great impact on other companies. Detecting this kind of impact helps users better to understand the affection of a specifi...
Article
Full-text available
Folksonomies can be viewed as large sources of informal se-mantics. Folksonomy tags can be interpreted as concepts that can be extracted from the social data and used as a basis for creating semantic structures. In the folksonomy the connection between these concepts and the tagged resources are explicit. However, to effectively use the extracted c...
Conference Paper
Full-text available
Folksonomies are becoming increasingly popular. They contain large amounts of data which can be mined and utilized for many tasks like visualization, browsing, information retrieval etc. An inherent problem of folksonomies is the lack of structure. In this paper we present an unsupervised approach for generating such structure based on a combinatio...
Conference Paper
Sentiment classification on product reviews has become a popular topic in the research community. In this paper, we propose an approach to generating multi-unigram features to enhance a negation-aware Naive Bayes classifier for sentiment classification on sentences of product reviews. We coin the term ”multi-unigram feature” to represent a new kin...
Conference Paper
Ontology evolution is the process of incrementally and consistently adapting an existing ontology to changes in the relevant domain. Semantic drift refers to how ontology concepts' intentions gradually change as the domain evolves. Normally, a semantic drift captures small domain changes that are hard to detect with traditional ontology management...
Article
An ontology is a formal conceptualization of a domain, specifying the concepts of the domain and the relations between them. It is however not a straight forward task to use this knowledge for information retrieval purposes. In this paper we describe the concept of an ontological profile, which is a semantic extension of an ontology where each onto...
Conference Paper
Full-text available
Ontology evolution is the process of incrementally and consistently adapting an existing ontology to changes in the relevant domain. Even though ontology management and versioning tools are now available, they are of limited use for ontology evolution unless the desired changes are known beforehand. Ontology learning toolsets are often employed, bu...
Conference Paper
Full-text available
Existing works on sentiment analysis on product reviews suffer from the following limitations: (1) The knowledge of hierarchical relationships of products attributes is not fully utilized. (2) Reviews or sentences mentioning several attributes associated with complicated sentiments are not dealt with very well. In this paper, we propose a novel HL-...
Article
Full-text available
In public administrations, the volume of stored data has been increasing over the past decades, leading to a growing amount of ageing information. Part of this ageing information is still in frequent use in ongoing business processes and data warehouses. However, one concern is the meaningful and trustworthy use of this ageing data in present appli...
Chapter
This chapter introduces semantic business process mining of SAP transaction logs. SAP systems are promising domains for semantic process mining as they contain transaction logs that are linked to large amounts of structured data. A challenge with process mining these transaction logs is that the core of SAP systems was not originally designed from...
Article
Full-text available
The petroleum industry is a technically challenging business with high investments, complex projects and operational structures. There are numerous companies and public offices in-volved in the exploitation of a new oil field, and there is a high de-gree of specialization among them. Even though standardization has been considered important in this...
Conference Paper
Full-text available
Ontologies are becoming increasingly more popular tools for many tasks, such as information integration, information retrieval, knowledge management and extraction etc. The cost and complexity of developing good ontologies is high, and therefore it is important to be able to verify the ontology and detect flaws early. In this paper we propose an ap...
Chapter
This chapter introduces semantic business process mining of SAP transaction logs. SAP systems are promising domains for semantic process mining as they contain transaction logs that are linked to large amounts of structured data. A challenge with process mining these transaction logs is that the core of SAP systems was not originally designed from...
Conference Paper
Full-text available
Ontology-driven search applications use ontological concepts either to index documents or to guide and understand the users. Since on- tologies by nature are domain-dependent and application-independent, though, there is no guarantee that their concepts are ecient in cat- egorizing and retrieving information from a specic,document index. This paper...
Conference Paper
Full-text available
Ontologies are conceptualizations of some domain, defining its concepts and their relationships. An interesting question is how do we relate the ontological concepts to the general vocabulary of the domain? In this paper we present the concept of ontological profiles, what they are, how they are constructed, and how they may be used. We propose tha...
Conference Paper
Most ontology learning tools concentrate on extracting concepts and instances from text corpora. There are some recent tools that employ linguistics or data mining to uncover concept relationships, but the results are mixed. Since relationships are semantically complex notions, it seems interesting to combine approaches that address different aspec...
Conference Paper
Ontology learning is the application of automatic tools to extract ontology concepts and relationships from domain text. Whereas ontology learning tools have been fairly successful in extracting concept candidates, it has proven difficult to detect relationships with the same level of accuracy. This paper discusses the use of association rules to e...
Conference Paper
The petroleum industry is a technically challenging business with highly specialized companies and complex operational structures. Several terminological standards have been introduced over the last few years, though they address particular disciplines and cannot help people collaborate efficiently across disciplines and organizational borders. Thi...
Conference Paper
Search is the process of locating information that matches a given query. Extract, Transform and Load (ETL) editors provide a user friendly and flexible environment for creating operation chains and digging into and explore data. In this paper, we describe the implementation of a process mining framework, the EVS Process Miner, which incorporates i...
Conference Paper
Ontology learning is the application of automatic tools to extract ontology concepts and relationships from domain text. Whereas ontology learning tools have been fairly successful in extracting concept candidates, it has proven difficult to detect relationships with the same level of accuracy. This paper discusses the use of association rules to e...