Jukka Huhtamäki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jukka Huhtamäki has a total of 97 co-authors. Here are the top co-authors by number of shared publications:
Kaisa Still
14 shared publications- Jari Jussila
Häme University of Applied Sciences, HAMK Design Factory, Finland
11 shared publications - Hannu Kärkkäinen
Tampere University
9 shared publications Neil Rubens
8 shared publications- Ekaterina Olshannikova
Tampere University, Tampere, Finland
7 shared publications - Anne-Maritta Tervakari
Intelligent Information Systems Laboratory, Department of Mathematics, Tampere University of Technology, Tampere, Finland
6 shared publications
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 502-513
Team Conversational AI: Introducing Effervesce
Erjon Skenderi, Salla-Maaria Laaksonen, Jukka Huhtamäki. Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 502-513
Open AccessTeam Conversational AI: Introducing Effervesce
Erjon Skenderi, Salla-Maaria Laaksonen, Jukka Huhtamäki. Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities. 2025.
- Open Access
- 1 January 2025
- Published by HICSS Conference Office
Introduction to the Minitrack on Platforms and Ecosystems: New Perspectives in the Era of Data, Analytics, and AI
- 1 January 2025
- Published by HICSS Conference Office
Open AccessIntroduction to the Minitrack on Platforms and Ecosystems: New Perspectives in the Era of Data, Analytics, and AI
- Open Access
- 16 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on the Web
- Vol. 18 (3) , 1-24
INCEPT: A Framework for Duplicate Posts Classification with Combined Text Representations
Dealing with many of the problems related to the quality of textual content online involves identifying similar content. Algorithmic solutions for duplicate content classification typically rely on text vector representation, which maps textual information into a set of features. Ideally, this representation would capture all aspects of the underlying text, including length, word frequencies, syntax, and semantics. While recent advancements in text representation have led to improved performance, a comprehensive approach that explicitly incorporates all text features has not yet been proposed. In this study, we present the INCEPT framework that utilizes multiple representation methods to detect duplicate text pairs, taking advantage of their individual strengths. The core of our approach involves using a stacking ensemble of pairwise vector distance measurements that are computed from multiple text representation methods. A stacking classifier then utilizes these distance scores as input and learns to identify duplicate posts. We assess the proposed framework’s effectiveness in identifying duplicate posts in an online Question and Answer platform. By combining several text representation methods, INCEPT performs well in the duplicate posts classification task. Our experiments demonstrate that specific framework configurations outperform the accuracy scores obtained from individual text representation methods. Therefore, we also infer that no single text representation method can independently capture a text’s features.
- 16 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on the Web
- Vol. 18 (3) , 1-24
Open AccessINCEPT: A Framework for Duplicate Posts Classification with Combined Text Representations
Dealing with many of the problems related to the quality of textual content online involves identifying similar content. Algorithmic solutions for duplicate content classification typically rely on text vector representation, which maps textual information into a set of features. Ideally, this representation would capture all aspects of the underlying text, including length, word frequencies, syntax, and semantics. While recent advancements in text representation have led to improved performance, a comprehensive approach that explicitly incorporates all text features has not yet been proposed. In this study, we present the INCEPT framework that utilizes multiple representation methods to detect duplicate text pairs, taking advantage of their individual strengths. The core of our approach involves using a stacking ensemble of pairwise vector distance measurements that are computed from multiple text representation methods. A stacking classifier then utilizes these distance scores as input and learns to identify duplicate posts. We assess the proposed framework’s effectiveness in identifying duplicate posts in an online Question and Answer platform. By combining several text representation methods, INCEPT performs well in the duplicate posts classification task. Our experiments demonstrate that specific framework configurations outperform the accuracy scores obtained from individual text representation methods. Therefore, we also infer that no single text representation method can independently capture a text’s features.
- 15 February 2024
- Published by Springer Nature
- p. 23-46
Encouraging Grading: Per Aspera Ad A-Stars
- Open Access
- 1 January 2024
- Published by HICSS Conference Office
Introduction to the Minitrack on Dynamics and Impacts of Platforms and Ecosystems
- 1 January 2024
- Published by HICSS Conference Office
Open AccessIntroduction to the Minitrack on Dynamics and Impacts of Platforms and Ecosystems
- 26 November 2023
- Published by Springer Nature
- p. 53-68
Streaming Death: Terrorist Violence, Post-death Data and the Digital Afterlife of Difficult Death
- 26 November 2023
- Published by Springer Nature
- p. 53-68
Streaming Death: Terrorist Violence, Post-death Data and the Digital Afterlife of Difficult Death
- Open Access
- 1 January 2023
- Published by HICSS Conference Office
Assessing Text Representation Methods on Tag Prediction Task for StackOverflow
A large part of knowledge evolves outside of the operations of an organization. Question and answer online social platforms provide an important source of information to explore the underlying communities. StackOverflow (SO) is one of the most popular question and answer platforms for developers, with more than 23 million questions asked. Organizing and categorizing data is crucial to manage knowledge in such large quantities. Questions posted on SO are assigned a set of tags and textual content of each question may contain coding syntax. In this paper, we evaluate the performance of multiple text representation methods in the task of predicting tags for SO questions and empirically prove the impact of code syntax in text representations. The SO dataset was sampled and questions without code syntax were identified. Two classical text representation methods consisting of BoW and TF-IDF were selected along four other methods based on pre-trained models including Fasttext, USE, Sentence-BERT and Sentence-RoBERTa. Multi-label k'th Nearest Neighbors classifier was used to learn and predict tags based on the similarities between feature-vector representations of the input data. Our results indicate a consistent superiority of the representations generated from Sentence-RoBERTa. Overall, the classifier achieved a 17% or higher improvement on F1 score when predicting tags for questions without any code syntax in content.
- 1 January 2023
- Published by HICSS Conference Office
Open AccessAssessing Text Representation Methods on Tag Prediction Task for StackOverflow
A large part of knowledge evolves outside of the operations of an organization. Question and answer online social platforms provide an important source of information to explore the underlying communities. StackOverflow (SO) is one of the most popular question and answer platforms for developers, with more than 23 million questions asked. Organizing and categorizing data is crucial to manage knowledge in such large quantities. Questions posted on SO are assigned a set of tags and textual content of each question may contain coding syntax. In this paper, we evaluate the performance of multiple text representation methods in the task of predicting tags for SO questions and empirically prove the impact of code syntax in text representations. The SO dataset was sampled and questions without code syntax were identified. Two classical text representation methods consisting of BoW and TF-IDF were selected along four other methods based on pre-trained models including Fasttext, USE, Sentence-BERT and Sentence-RoBERTa. Multi-label k'th Nearest Neighbors classifier was used to learn and predict tags based on the similarities between feature-vector representations of the input data. Our results indicate a consistent superiority of the representations generated from Sentence-RoBERTa. Overall, the classifier achieved a 17% or higher improvement on F1 score when predicting tags for questions without any code syntax in content.
- Open Access
- 1 January 2023
- Published by HICSS Conference Office
Introduction to the Minitrack on Managing the Dynamics of Platforms and Ecosystems
- 1 January 2023
- Published by HICSS Conference Office
Open AccessIntroduction to the Minitrack on Managing the Dynamics of Platforms and Ecosystems
- Open Access
- 16 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 89-101
What Supports Serendipity on Twitter? Online Survey on the Role of Technology Characteristics and Their Use
Serendipity experiences are highly desirable in work life, considering both individuals’ learning and organizational innovation capacity. This study looks into information and social serendipity in the context of Twitter. While Twitter can be viewed as a fruitful platform for serendipity to emerge, there is little understanding of what technology characteristics and use practices contribute to such experiences in work-related use. Drawing from the functional affordances theory, the paper investigates the role of presenteeism, self-disclosure, recommendation quality and pace of change, and different types of Twitter use as possible antecedents of serendipity. A cross-sectional international online survey was conducted with 473 respondents who actively use Twitter in their work. An exploratory factor analysis was performed, followed by linear regression analysis to identify relevant statistical associations. The findings indicate that presenteeism (i.e., the fundamental element of reachability) seems to have an effect on serendipity while the more designable characteristics, like the quality of recommendations, do not. Overall, the findings imply that serendipity experiences are primarily explained by individual characteristics like personality and specific ways of using Twitter. This is amongst the first studies on the role of Twitter characteristics as functional affordances in the formation of serendipity. The extensive empirical study contributes a detailed analysis of the antecedents of serendipity and opens avenues for research and design to identify new serendipity-inducing mechanisms.
- 16 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 89-101
Open AccessWhat Supports Serendipity on Twitter? Online Survey on the Role of Technology Characteristics and Their Use
Serendipity experiences are highly desirable in work life, considering both individuals’ learning and organizational innovation capacity. This study looks into information and social serendipity in the context of Twitter. While Twitter can be viewed as a fruitful platform for serendipity to emerge, there is little understanding of what technology characteristics and use practices contribute to such experiences in work-related use. Drawing from the functional affordances theory, the paper investigates the role of presenteeism, self-disclosure, recommendation quality and pace of change, and different types of Twitter use as possible antecedents of serendipity. A cross-sectional international online survey was conducted with 473 respondents who actively use Twitter in their work. An exploratory factor analysis was performed, followed by linear regression analysis to identify relevant statistical associations. The findings indicate that presenteeism (i.e., the fundamental element of reachability) seems to have an effect on serendipity while the more designable characteristics, like the quality of recommendations, do not. Overall, the findings imply that serendipity experiences are primarily explained by individual characteristics like personality and specific ways of using Twitter. This is amongst the first studies on the role of Twitter characteristics as functional affordances in the formation of serendipity. The extensive empirical study contributes a detailed analysis of the antecedents of serendipity and opens avenues for research and design to identify new serendipity-inducing mechanisms.