Learning Preferences with Kernel-Based Methods

Learning of preference relations has recently received significant attention in machine learning community. It is closely related to the classification and regression analysis and can be reduced to these tasks. However, preference learning involves prediction of ordering of the data points rather than prediction of a single numerical value as in case of regression or a class label as in case of classification. Therefore, studying preference relations within a separate framework facilitates not only better theoretical understanding of the problem, but also motivates development of the efficient algorithms for the task. Preference learning has many applications in domains such as information retrieval, bioinformatics, natural language processing, etc. For example, algorithms that learn to rank are frequently used in search engines for ordering documents retrieved by the query. Preference learning methods have been also applied to collaborative filtering problems for predicting individual customer choices from the vast amount of user generated feedback. In this thesis we propose several algorithms for learning preference relations. These algorithms stem from well founded and robust class of regularized least-squares methods and have many attractive computational properties. In order to improve the performance of our methods, we introduce several non-linear kernel functions. Thus, contribution of this thesis is twofold: kernel functions for structured data that are used to take advantage of various non-vectorial data representations and the preference learning algorithms that are suitable for different tasks, namely efficient learning of preference relations, learning with large amount of training data, and semi-supervised preference learning. Proposed kernel-based algorithms and kernels are applied to the parse ranking task in natural language processing, document ranking in information retrieval, and remote homology detection in bioinformatics domain. Training of kernel-based ranking algorithms can be infeasible when the size of the training set is large. This problem is addressed by proposing a preference learning algorithm whose computation complexity scales linearly with the number of training data points. We also introduce sparse approximation of the algorithm that can be efficiently trained with large amount of data. For situations when small amount of labeled data but a large amount of unlabeled data is available, we propose a co-regularized preference learning algorithm. To conclude, the methods presented in this thesis address not only the problem of the efficient training of the algorithms but also fast regularization parameter selection, multiple output prediction, and cross-validation. Furthermore, proposed algorithms lead to notably better performance in many preference learning tasks considered.

Tietämyksen kasvattamisen keinot Case: Handwise Oy:n tietämyksen kasvattaminen yksilön ja organisaation oppimisen keinoin

Työn tavoitteena oli selvittää yksilön ja organisaation tietämystä sekä niiden kasvattamista. Tarkoituksena oli löytää yksilön ja organisaation tietämyksen yhdistäviä tekijöitä. Tutkimusmetodologia oli empiirinen deskriptiivinen tutkimus ja tutkimusmenetelmä oli kvalitatiivinen perustuen kymmeneen teemahaastatteluun. Tutkimuksen tuloksena oli, että tietotyöntekijät kasvattavat omaa ja organisaation tietämystä samankaltaisin keinoin, eikä niiden välillä mielletty olevan suurtakaan eroa. Työssä kokeminen yrityksen ja erehdyksen kautta kerrottiin tärkeimmäksi menetelmäksi kasvattaa omaa tietämystä. Kirjoja arvostettiin erityisen paljon tietämyksen kasvattamisessa ja se ohitti tiedon lähteenä jopa internetin. Työkollegat olivat kolmas tärkeä tietämyksen lähde. Kaksi tärkeintä edellytystä tietämyksen kasvattamisessa olivat opiskelun aikana saatu tietopohja sekä oma kiinnostus ja motivaatio. Organisaation tietämyksen kasvattamisessa tärkeimmäksi tekijäksi nousivat dokumentointi, virheistä oppiminen, sisäinen kommunikointi, tietojärjestelmät ja avoin organisaatiokulttuuri. Tutkimuksen perusteella syntyi kolmivaiheinen malli tietämyksen kasvattamisen kehästä, jonka elementit ovat edellytykset, lähteet ja menetelmät. Kehän keskellä on työssä oppiminen, joka on tärkein tekijä tietämyksen kasvattamisessa. Case-yrityksen toiminta oppivana organisaationa osoitti, että yrityksessä tulisi panostaa erityisesti oppimisen tukemiseen ja johtamiseen. Myös tiedon dokumentointi ja muuttaminen avoimeen muotoon sekä yrityksen prosessit tarvitsevat selkiyttämistä. Organisaation avoimuus ja ilmapiiri osoittautuivat hyviksi, mikä auttaa osaltaan tietämyksen kasvattamista.

Designing new learning experiences? : exploring corporate E-learners’ self-regulated learning

The context of this study is corporate e-learning, with an explicit focus on how digital learning design can facilitate self-regulated learning (SRL). The field of e-learning is growing rapidly. An increasing number of corporations use digital technology and elearning for training their work force and customers. E-learning may offer economic benefits, as well as opportunities for interaction and communication that traditional teaching cannot provide. However, the evolving variety of digital learning contexts makes new demands on learners, requiring them to develop strategies to adapt and cope with novel learning tools. This study derives from the need to learn more about learning experiences in digital contexts in order to be able to design these properly for learning. The research question targets how the design of an e-learning course influences participants’ self-regulated learning actions and intentions. SRL involves learners’ ability to exercise agency in their learning. Micro-level SRL processes were targeted by exploring behaviour, cognition, and affect/motivation in relation to the design of the digital context. Two iterations of an e-learning course were tested on two groups of participants (N=17). However, the exploration of SRL extends beyond the educational design research perspective of comparing the effects of the changes to the course designs. The study was conducted in a laboratory with each participant individually. Multiple types of data were collected. However, the results presented in this thesis are based on screen observations (including eye tracking) and video-stimulated recall interviews. These data were integrated in order to achieve a broad perspective on SRL. The most essential change evident in the second course iteration was the addition of feedback during practice and the final test. Without feedback on actions there was an observable difference between those who were instruction-directed and those who were self-directed in manipulating the context and, thus, persisted whenever faced with problems. In the second course iteration, including the feedback, this kind of difference was not found. Feedback provided the tipping point for participants to regulate their learning by identifying their knowledge gaps and to explore the learning context in a targeted manner. Furthermore, the course content was consistently seen from a pragmatic perspective, which influenced the participants’ choice of actions, showing that real life relevance is an important need of corporate learners. This also relates to assessment and the consideration of its purpose in relation to participants’ work situation. The rigidity of the multiple choice questions, focusing on the memorisation of details, influenced the participants to adapt to an approach for surface learning. It also caused frustration in cases where the participants’ epistemic beliefs were incompatible with this kind of assessment style. Triggers of positive and negative emotions could be categorized into four levels: personal factors, instructional design of content, interface design of context, and technical solution. In summary, the key design choices for creating a positive learning experience involve feedback, flexibility, functionality, fun, and freedom. The design of the context impacts regulation of behaviour, cognition, as well as affect and motivation. The learners’ awareness of these areas of regulation in relation to learning in a specific context is their ability for design-based epistemic metareflection. I describe this metareflection as knowing how to manipulate the context behaviourally for maximum learning, being metacognitively aware of one’s learning process, and being aware of how emotions can be regulated to maintain volitional control of the learning situation. Attention needs to be paid to how the design of a digital learning context supports learners’ metareflective development as digital learners. Every digital context has its own affordances and constraints, which influence the possibilities for micro-level SRL processes. Empowering learners in developing their ability for design-based epistemic metareflection is, therefore, essential for building their digital literacy in relation to these affordances and constraints. It was evident that the implementation of e-learning in the workplace is not unproblematic and needs new ways of thinking about learning and how we create learning spaces. Digital contexts bring a new culture of learning that demands attitude change in how we value knowledge, measure it, define who owns it, and who creates it. Based on the results, I argue that digital solutions for corporate learning ought to be built as an integrated system that facilitates socio-cultural connectivism within the corporation. The focus needs to shift from designing static e-learning material to managing networks of social meaning negotiation as part of a holistic corporate learning ecology.

Messaging Application Engine for Symbian Platform

Tämä diplomityö kuvaa viestintä sovelluksen ytimen kehitystyön Symbian-alustalle. Koko sovelluksen vaatimuksena oli vastaamattomiin puheluihin vastaaminen ennalta määritellyillä tekstiviesteillä käyttäjän määrittelemien sääntöjen mukaisesti. Ei-toiminnallisia vaatimuksia olivat resurssien käytön vähentäminen ja uudelleenkäytön mahdollistaminen. Täten tämän työn tavoitteena oli kehittää ydin, joka kapseloi sovelluksen sellaisen toiminnallisuuden, joka on käyttöliittymästä riippumatonta ja uudelleenkäytettävää. Kehitystyössä ohjasi Unified Process, joka on iteroiva, käyttötapauksien ohjaama ja arkkitehtuurikeskeinen ohjelmistoprosessi. Se kannusti käyttämään myös muita teollisuudenalan vakiintuneita menetelmiä, kuten suunnittelumalleja ja visuaalista mallintamista käyttäen Unified Modelling Languagea. Suunnittelumalleja käytettiin kehitystyön aikana ja ohjelmisto mallinnettiin visuaalisesti suunnittelun edistämiseksi ja selkiyttämiseksi. Alustan palveluita käytettiin hyväksi kehitysajan ja resurssien käytön minimoimiseksi. Ytimen päätehtäviksi määrättiin viestien lähettäminen sekä sääntöjen talletus ja tarkistaminen. Sovelluksen eri alueet, eli sovelluspalvelin ja käyttöliittymää, pystyivät käyttämään ydintä ja sillä ei ollut riippuvuuksia käyttöliittymätasolle. Täten resurssien käyttö väheni ja uudelleenkäytettävyys lisääntyi. Viestien lähettäminen toteutettiin Symbian-alustan menetelmin. Sääntöjen tallettamiseen tehtiin tallennuskehys, joka eristää sääntöjen sisäisen ja ulkoisen muodon. Tässä tapauksessa ulkoiseksi tallennustavaksi valittiin relaatiotietokanta. Sääntöjen tarkastaminen toteutettiin tavanomaisella olioiden yhteistoiminnalla. Päätavoite saavutettiin. tämä ja muut hyviksi arvioidut lopputulokset, kuten uudelleenkäytettävyys ja vähentynyt resurssien käyttö, arveltiin juontuvan suunnittelumallien ja Unified Processin käytöstä. Kyseiset menetelmät osoittivat mukautuvansa pieniinkin projekteihin. Menetelmien todettiin myös tukevan ja kannustavan kehitystyön aikaista oppimista, mikä oli välttämätöntä tässä tapauksessa.

The Key Features of Knowledge and Knowledge Management in Product Development Process

Tutkimusongelmana oli kuinka tiedon johtamisella voidaan edesauttaa tuotekehitysprosessia. Mitkä ovat ne avaintekijät tietoympäristössä kuin myös itse tiedossa, joilla on merkitystä erityisesti tuotekehitysprosessin arvon muodostumiseen ja prosessien kehittämiseen? Tutkimus on laadullinen Case-tutkimus. Tutkimusongelmat on ensin selvitetty kirjallisuuden avulla, jonka jälkeen teoreettinen viitekehys on rakennettu tutkimaan rajattua ongelma-aluetta case-yrityksestä. Empiirisen tutkimuksen materiaali koostuu pääasiallisesti henkilökohtaisten teemahaastattelujen aineistosta. Tulokset merkittävimmistä tiedon hyväksikäytön haittatekijöistä, kuten myös parannusehdotukset on lajiteltu teoreettisessa viitekehyksessä esitettyjen oletustekijöiden mukaan. Haastatteluissa saadut vastaukset tukevat kirjallisuudesta ja alan ammattilaiselta saatua käsitystä tärkeimmistä vaikuttavista tekijöistä. Tärkeimmät toimenpiteet ja aloitteet joilla parannettaisiin tiedon muodostumista, koskivat ennnen kaikkea työnteon ulkoisia olosuhteita, eikä niinkään tiedon muodostumisen prosessia itseään. Merkittävimpiä haittatekijöitä olivat kultturiin, fyysiseen ja henkiseen tilaan ja henkilöstöresursseihin liittyvät ongelmat. Ratkaisuja ongelmiin odotettiin saatavan lähinnä tietotekniikan, henkilöstöresurssien ja itse tiedon muokkaamisen avulla. Tuotekehitysprosessin ydin tietovirtojen ja –pääomien luokittelu ja tulkitseminen tiedon muodostusta kuvaavan Learning Spiralin avulla antoi lähinnä teoreettisia viitteitä siitä millaisia keinoja on olemassa tiedon lisäämiseen ja jakamiseen eri tietotyypeittäin. Tulosten perusteella caseyrityksessä pitäisi kiinnittää erityistä huomiota tiedon dokumentointiin ja jakamiseen erityisesti sen tiedon osalta, joka on organisaatiossa vain harvalla ja/tai luonteeltaan hyvin tacitia.

Thinking Outside the Box: Enhancing Science Teaching by Combining (Instead of Contrasting) Laboratory and Simulation Activities

The focus of the present work was on 10- to 12-year-old elementary school students’ conceptual learning outcomes in science in two specific inquiry-learning environments, laboratory and simulation. The main aim was to examine if it would be more beneficial to combine than contrast simulation and laboratory activities in science teaching. It was argued that the status quo where laboratories and simulations are seen as alternative or competing methods in science teaching is hardly an optimal solution to promote students’ learning and understanding in various science domains. It was hypothesized that it would make more sense and be more productive to combine laboratories and simulations. Several explanations and examples were provided to back up the hypothesis. In order to test whether learning with the combination of laboratory and simulation activities can result in better conceptual understanding in science than learning with laboratory or simulation activities alone, two experiments were conducted in the domain of electricity. In these experiments students constructed and studied electrical circuits in three different learning environments: laboratory (real circuits), simulation (virtual circuits), and simulation-laboratory combination (real and virtual circuits were used simultaneously). In order to measure and compare how these environments affected students’ conceptual understanding of circuits, a subject knowledge assessment questionnaire was administered before and after the experimentation. The results of the experiments were presented in four empirical studies. Three of the studies focused on learning outcomes between the conditions and one on learning processes. Study I analyzed learning outcomes from experiment I. The aim of the study was to investigate if it would be more beneficial to combine simulation and laboratory activities than to use them separately in teaching the concepts of simple electricity. Matched-trios were created based on the pre-test results of 66 elementary school students and divided randomly into a laboratory (real circuits), simulation (virtual circuits) and simulation-laboratory combination (real and virtual circuits simultaneously) conditions. In each condition students had 90 minutes to construct and study various circuits. The results showed that studying electrical circuits in the simulation–laboratory combination environment improved students’ conceptual understanding more than studying circuits in simulation and laboratory environments alone. Although there were no statistical differences between simulation and laboratory environments, the learning effect was more pronounced in the simulation condition where the students made clear progress during the intervention, whereas in the laboratory condition students’ conceptual understanding remained at an elementary level after the intervention. Study II analyzed learning outcomes from experiment II. The aim of the study was to investigate if and how learning outcomes in simulation and simulation-laboratory combination environments are mediated by implicit (only procedural guidance) and explicit (more structure and guidance for the discovery process) instruction in the context of simple DC circuits. Matched-quartets were created based on the pre-test results of 50 elementary school students and divided randomly into a simulation implicit (SI), simulation explicit (SE), combination implicit (CI) and combination explicit (CE) conditions. The results showed that when the students were working with the simulation alone, they were able to gain significantly greater amount of subject knowledge when they received metacognitive support (explicit instruction; SE) for the discovery process than when they received only procedural guidance (implicit instruction: SI). However, this additional scaffolding was not enough to reach the level of the students in the combination environment (CI and CE). A surprising finding in Study II was that instructional support had a different effect in the combination environment than in the simulation environment. In the combination environment explicit instruction (CE) did not seem to elicit much additional gain for students’ understanding of electric circuits compared to implicit instruction (CI). Instead, explicit instruction slowed down the inquiry process substantially in the combination environment. Study III analyzed from video data learning processes of those 50 students that participated in experiment II (cf. Study II above). The focus was on three specific learning processes: cognitive conflicts, self-explanations, and analogical encodings. The aim of the study was to find out possible explanations for the success of the combination condition in Experiments I and II. The video data provided clear evidence about the benefits of studying with the real and virtual circuits simultaneously (the combination conditions). Mostly the representations complemented each other, that is, one representation helped students to interpret and understand the outcomes they received from the other representation. However, there were also instances in which analogical encoding took place, that is, situations in which the slightly discrepant results between the representations ‘forced’ students to focus on those features that could be generalised across the two representations. No statistical differences were found in the amount of experienced cognitive conflicts and self-explanations between simulation and combination conditions, though in self-explanations there was a nascent trend in favour of the combination. There was also a clear tendency suggesting that explicit guidance increased the amount of self-explanations. Overall, the amount of cognitive conflicts and self-explanations was very low. The aim of the Study IV was twofold: the main aim was to provide an aggregated overview of the learning outcomes of experiments I and II; the secondary aim was to explore the relationship between the learning environments and students’ prior domain knowledge (low and high) in the experiments. Aggregated results of experiments I & II showed that on average, 91% of the students in the combination environment scored above the average of the laboratory environment, and 76% of them scored also above the average of the simulation environment. Seventy percent of the students in the simulation environment scored above the average of the laboratory environment. The results further showed that overall students seemed to benefit from combining simulations and laboratories regardless of their level of prior knowledge, that is, students with either low or high prior knowledge who studied circuits in the combination environment outperformed their counterparts who studied in the laboratory or simulation environment alone. The effect seemed to be slightly bigger among the students with low prior knowledge. However, more detailed inspection of the results showed that there were considerable differences between the experiments regarding how students with low and high prior knowledge benefitted from the combination: in Experiment I, especially students with low prior knowledge benefitted from the combination as compared to those students that used only the simulation, whereas in Experiment II, only students with high prior knowledge seemed to benefit from the combination relative to the simulation group. Regarding the differences between simulation and laboratory groups, the benefits of using a simulation seemed to be slightly higher among students with high prior knowledge. The results of the four empirical studies support the hypothesis concerning the benefits of using simulation along with laboratory activities to promote students’ conceptual understanding of electricity. It can be concluded that when teaching students about electricity, the students can gain better understanding when they have an opportunity to use the simulation and the real circuits in parallel than if they have only the real circuits or only a computer simulation available, even when the use of the simulation is supported with the explicit instruction. The outcomes of the empirical studies can be considered as the first unambiguous evidence on the (additional) benefits of combining laboratory and simulation activities in science education as compared to learning with laboratories and simulations alone.

Conceptions of mathematics teacher education : thoughts among teacher educators in Tanzania

This study addresses the question of teacher educators’ conceptions of mathematics teacher education (MTE) in teacher colleges in Tanzania, and their thoughts on how to further develop it. The tension between exponents of content as opposed to pedagogy has continued to cause challenging conceptual differences, which also influences what teacher educators conceive as desirable in the development of this domain. This tension is connected to the dissatisfaction of parents and teachers with the failure of school mathematics. From this point of view, the overall aim was to identify and describe teacher educators’ various conceptions of MTE. Inspired by the debate among teacher educators about what the balance should be between subject matter and pedagogical knowledge, it was important to look at the theoretical faces of MTE. The theoretical background involved the review of what is visible in MTE, what is yet to be known and the challenges within the practice. This task revealed meanings, perspectives in MTE, professional development and assessment. To do this, two questions were asked, to which no clear solutions satisfactorily existed. The questions to guide the investigation were, firstly, what are teacher educators’ conceptions of MTE, and secondly, what are teacher educators’ thoughts on the development of MTE? The two questions led to the choice of phenomenography as the methodological approach. Against the guiding questions, 27 mathematics teacher educators were interviewed in relation to the first question, while 32 responded to an open-ended questionnaire regarding question two. The interview statements as well as the questionnaire responses were coded and analysed (classified). The process of classification generated patterns of qualitatively different ways of seeing MTE. The results indicate that MTE is conceived as a process of learning through investigation, fostering inspiration, an approach to learning with an emphasis on problem solving, and a focus on pedagogical knowledge and skills in the process of teaching and learning. In addition, the teaching and learning of mathematics is seen as subject didactics with a focus on subject matter and as an organized integration of subject matter, pedagogical knowledge and some school practice; and also as academic content knowledge in which assessment is inherent. The respondents also saw the need to build learner-educator relationships. Finally, they emphasized taking advantage of teacher educators’ neighbourhood learning groups, networking and collaboration as sustainable knowledge and skills sharing strategies in professional development. Regarding desirable development, teacher educators’ thoughts emphasised enhancing pedagogical knowledge and subject matter, and to be determined by them as opposed to conventional top-down seminars and workshops. This study has revealed various conceptions and thoughts about MTE based on teacher educators´ diverse history of professional development in mathematics. It has been reasonably substantiated that some teacher educators teach school mathematics in the name of MTE, hardly distinguishing between the role and purpose of the two in developing a mathematics teacher. What teacher educators conceive as MTE and what they do regarding the education of teachers of mathematics revealed variations in terms of seeing the phenomenon of interest. Within limits, desirable thoughts shed light on solutions to phobias, and in the same way low self-esteem and stigmatization call for the building of teacher educator-student teacher relationships.

Johtamisen keinot tiimien tiedonvaihdon ja oppimisen edistämiseksi logistiikkayrityksessä

Tämän päivän nopeasti muuttuvassa toimintaympäristössä tiedon ja oppimisen merkitys korostuu. Tiimityön lisäännyttyä on tiimien oppiminen merkittävä osa organisaation oppimista. Tässä tutkimuksessa tiimien oppimista tarkastellaan työssäoppimisen kautta. Tutkimuksen case –yrityksenä on logistiikkayritys. Tutkimuksen empiirinen osuus toteutettiin teemahaastatteluin. Haastateltavia oli yhteensä kaksitoista henkilöä. Haastatteluissa olivat edustettuina tuotannon työntekijät, toimihenkilöt ja esimiehet. Tutkimuksen tuloksina havaittiin, että johdon ja esimiesten rooli on äärimmäisen tärkeä tiimien oppimisen edistämisen kannalta. Johto voi edistää tiimien oppimista osoittamalla kiinnostusta ja luottamusta tiimien työtä kohtaan, sitoutumalla oppimisen mahdollistamiseen ja kannustamalla tiimejä oppimaan myös omalla esimerkillään.

Nursing students and older people nursing. Towards a future career

The purpose of this two-phased study is to examine the interest of nursing students in choosing a career in older people nursing. First, the scoping phase explores the different premises for choosing older people nursing as a career. Second, the evaluation phase investigates the outcomes of the developed educational intervention involving older people as promoters of choosing a career in older people nursing, factors related to these outcomes, and experiences with educational intervention. The ultimate goal is to encourage more nursing students to choose older people nursing as their career. The scoping phase applies an exploratory design and centres around a descriptive, cross-sectional survey, documentary research and a scoping literature review. The information sources for this phase include 183 nursing students, 101 newspaper articles and 66 research articles. The evaluation phase applies a quasi-experimental design and a pre-post-test design with a non-equivalent comparison group and a post-intervention survey. The information sources for this phase include 87 nursing students and 43 older people. In both phases, statistical and narrative methods are applied in the data analysis. Nursing students neutrally regarded the idea of a career in older people nursing. The most consistent factors related to the nursing students’ career plans in older people nursing were found to be nursing work experience and various educational preparations in the field. Nursing students in the intervention group (n=40) were more interested in older people nursing and had more positive attitudes towards older people than did students in the comparison group (n=36). However, in both groups, the interest that students had at the baseline was associated with the interest at the one-month follow-up. There were no significant differences between the groups in terms of the students’ knowledge levels about ageing. The nursing students and older people alike highly appreciated participating in the educational intervention. It seems possible to positively impact nursing students and their choices to pursue careers in older people nursing, at least in the short-term. The involvement of older people as promoters of this career choice provides one encouraging alternative for impacting students’ career choices, but additional research is needed.

Predicting diffusion of innovations with self-organisation and machine learning

The main subject of this master's thesis was predicting diffusion of innovations. The prediction was done in a special case: product has been available in some countries, and based on its diffusion in those countries the prediction is done for other countries. The prediction was based on finding similar countries with Self-Organizing Map~(SOM), using parameters of countries. Parameters included various economical and social key figures. SOM was optimised for different products using two different methods: (a) by adding diffusion information of products to the country parameters, and (b) by weighting the country parameters based on their importance for the diffusion of different products. A novel method using Differential Evolution (DE) was developed to solve the latter, highly non-linear optimisation problem. Results were fairly good. The prediction method seems to be on a solid theoretical foundation. The results based on country data were good. Instead, optimisation for different products did not generally offer clear benefit, but in some cases the improvement was clearly noticeable. The weights found for the parameters of the countries with the developed SOM optimisation method were interesting, and most of them could be explained by properties of the products.

Promoting Programming Learning. Engagement, Automatic Assessment with Immediate Feedback in Visualizations

The skill of programming is a key asset for every computer science student. Many studies have shown that this is a hard skill to learn and the outcomes of programming courses have often been substandard. Thus, a range of methods and tools have been developed to assist students’ learning processes. One of the biggest fields in computer science education is the use of visualizations as a learning aid and many visualization based tools have been developed to aid the learning process during last few decades. Studies conducted in this thesis focus on two different visualizationbased tools TRAKLA2 and ViLLE. This thesis includes results from multiple empirical studies about what kind of effects the introduction and usage of these tools have on students’ opinions and performance, and what kind of implications there are from a teacher’s point of view. The results from studies in this thesis show that students preferred to do web-based exercises, and felt that those exercises contributed to their learning. The usage of the tool motivated students to work harder during their course, which was shown in overall course performance and drop-out statistics. We have also shown that visualization-based tools can be used to enhance the learning process, and one of the key factors is the higher and active level of engagement (see. Engagement Taxonomy by Naps et al., 2002). The automatic grading accompanied with immediate feedback helps students to overcome obstacles during the learning process, and to grasp the key element in the learning task. These kinds of tools can help us to cope with the fact that many programming courses are overcrowded with limited teaching resources. These tools allows us to tackle this problem by utilizing automatic assessment in exercises that are most suitable to be done in the web (like tracing and simulation) since its supports students’ independent learning regardless of time and place. In summary, we can use our course’s resources more efficiently to increase the quality of the learning experience of the students and the teaching experience of the teacher, and even increase performance of the students. There are also methodological results from this thesis which contribute to developing insight into the conduct of empirical evaluations of new tools or techniques. When we evaluate a new tool, especially one accompanied with visualization, we need to give a proper introduction to it and to the graphical notation used by tool. The standard procedure should also include capturing the screen with audio to confirm that the participants of the experiment are doing what they are supposed to do. By taken such measures in the study of the learning impact of visualization support for learning, we can avoid drawing false conclusion from our experiments. As computer science educators, we face two important challenges. Firstly, we need to start to deliver the message in our own institution and all over the world about the new – scientifically proven – innovations in teaching like TRAKLA2 and ViLLE. Secondly, we have the relevant experience of conducting teaching related experiment, and thus we can support our colleagues to learn essential know-how of the research based improvement of their teaching. This change can transform academic teaching into publications and by utilizing this approach we can significantly increase the adoption of the new tools and techniques, and overall increase the knowledge of best-practices. In future, we need to combine our forces and tackle these universal and common problems together by creating multi-national and multiinstitutional research projects. We need to create a community and a platform in which we can share these best practices and at the same time conduct multi-national research projects easily.

Biomedical Event Extraction with Machine Learning

Biomedical natural language processing (BioNLP) is a subfield of natural language processing, an area of computational linguistics concerned with developing programs that work with natural language: written texts and speech. Biomedical relation extraction concerns the detection of semantic relations such as protein-protein interactions (PPI) from scientific texts. The aim is to enhance information retrieval by detecting relations between concepts, not just individual concepts as with a keyword search. In recent years, events have been proposed as a more detailed alternative for simple pairwise PPI relations. Events provide a systematic, structural representation for annotating the content of natural language texts. Events are characterized by annotated trigger words, directed and typed arguments and the ability to nest other events. For example, the sentence “Protein A causes protein B to bind protein C” can be annotated with the nested event structure CAUSE(A, BIND(B, C)). Converted to such formal representations, the information of natural language texts can be used by computational applications. Biomedical event annotations were introduced by the BioInfer and GENIA corpora, and event extraction was popularized by the BioNLP'09 Shared Task on Event Extraction. In this thesis we present a method for automated event extraction, implemented as the Turku Event Extraction System (TEES). A unified graph format is defined for representing event annotations and the problem of extracting complex event structures is decomposed into a number of independent classification tasks. These classification tasks are solved using SVM and RLS classifiers, utilizing rich feature representations built from full dependency parsing. Building on earlier work on pairwise relation extraction and using a generalized graph representation, the resulting TEES system is capable of detecting binary relations as well as complex event structures. We show that this event extraction system has good performance, reaching the first place in the BioNLP'09 Shared Task on Event Extraction. Subsequently, TEES has achieved several first ranks in the BioNLP'11 and BioNLP'13 Shared Tasks, as well as shown competitive performance in the binary relation Drug-Drug Interaction Extraction 2011 and 2013 shared tasks. The Turku Event Extraction System is published as a freely available open-source project, documenting the research in detail as well as making the method available for practical applications. In particular, in this thesis we describe the application of the event extraction method to PubMed-scale text mining, showing how the developed approach not only shows good performance, but is generalizable and applicable to large-scale real-world text mining projects. Finally, we discuss related literature, summarize the contributions of the work and present some thoughts on future directions for biomedical event extraction. This thesis includes and builds on six original research publications. The first of these introduces the analysis of dependency parses that leads to development of TEES. The entries in the three BioNLP Shared Tasks, as well as in the DDIExtraction 2011 task are covered in four publications, and the sixth one demonstrates the application of the system to PubMed-scale text mining.

Sentence Compression with Supervised Machine Learning

The subject of the thesis is automatic sentence compression with machine learning, so that the compressed sentences remain both grammatical and retain their essential meaning. There are multiple possible uses for the compression of natural language sentences. In this thesis the focus is generation of television program subtitles, which often are compressed version of the original script of the program. The main part of the thesis consists of machine learning experiments for automatic sentence compression using different approaches to the problem. The machine learning methods used for this work are linear-chain conditional random fields and support vector machines. Also we take a look which automatic text analysis methods provide useful features for the task. The data used for machine learning is supplied by Lingsoft Inc. and consists of subtitles in both compressed an uncompressed form. The models are compared to a baseline system and comparisons are made both automatically and also using human evaluation, because of the potentially subjective nature of the output. The best result is achieved using a CRF - sequence classification using a rich feature set. All text analysis methods help classification and most useful method is morphological analysis. Tutkielman aihe on suomenkielisten lauseiden automaattinen tiivistäminen koneellisesti, niin että lyhennetyt lauseet säilyttävät olennaisen informaationsa ja pysyvät kieliopillisina. Luonnollisen kielen lauseiden tiivistämiselle on monta käyttötarkoitusta, mutta tässä tutkielmassa aihetta lähestytään television ohjelmien tekstittämisen kautta, johon käytännössä kuuluu alkuperäisen tekstin lyhentäminen televisioruudulle paremmin sopivaksi. Tutkielmassa kokeillaan erilaisia koneoppimismenetelmiä tekstin automaatiseen lyhentämiseen ja tarkastellaan miten hyvin erilaiset luonnollisen kielen analyysimenetelmät tuottavat informaatiota, joka auttaa näitä menetelmiä lyhentämään lauseita. Lisäksi tarkastellaan minkälainen lähestymistapa tuottaa parhaan lopputuloksen. Käytetyt koneoppimismenetelmät ovat tukivektorikone ja lineaarisen sekvenssin mallinen CRF. Koneoppimisen tukena käytetään tekstityksiä niiden eri käsittelyvaiheissa, jotka on saatu Lingsoft OY:ltä. Luotuja malleja vertaillaan Lopulta mallien lopputuloksia evaluoidaan automaattisesti ja koska teksti lopputuksena on jossain määrin subjektiivinen myös ihmisarviointiin perustuen. Vertailukohtana toimii kirjallisuudesta poimittu menetelmä. Tutkielman tuloksena paras lopputulos saadaan aikaan käyttäen CRF sekvenssi-luokittelijaa laajalla piirrejoukolla. Kaikki kokeillut teksin analyysimenetelmät auttavat luokittelussa, joista tärkeimmän panoksen antaa morfologinen analyysi.

Finnish Preclinical and Clinical Medical Students as Strategic L2 English Learners: Language Learning Strategies and Communicating with Patients

This thesis focused on medical students’ language learning strategies for patient encounters. The research questions concerned the types of learning strategies that medical students use and the differences between the preclinical students and the clinical students, two groups who have had varying amounts of experience with patients. Additionally, strategy use was examined through activity systems to gain information on the context of language learning strategy use in order to learn language for patient encounters. In total, 130 first-year medical students (preclinical) and 39 fifth-year medical students (clinical) participated in the study by filling in a questionnaire on language learning strategies. In addition, two students were interviewed in order to create activity systems for the medical students at different stages of their studies. The study utilised both quantitative and qualitative research methods; the analysis of the results relies on Oxford’s Strategic Self-Regulation Model in the quantitative part and on activity theory in the qualitative part. The theoretical sections of the study introduced earlier research and theories regarding English for specific purposes, language learning strategies and activity theory. The results indicated that the medical students use affective, sociocultural-interactive and metasociocultural-interactive strategies often and avoid using negative strategies, which hinder language learning or cease communication altogether. Slight differences between the preclinical and clinical students were found, as clinical students appear to use affective and metasociocultural-interactive strategies more frequently compared to the preclinical students. The activity systems of the two students interviewed were rather similar. The students were at different stages of their studies, but their opinions were very similar. Both reported the object of learning to be mutual understanding between the patient and the doctor, which in part explains the preference for strategies that support communication and interaction. The results indicate that the nature of patient encounters affects the strategy use of the medical students at least to some extent.