Search results for "NTIME"
showing 10 items of 400 documents
Dealing with a small amount of data : developing Finnish sentiment analysis
2022
Sentiment analysis has been more and more prominently visible among all natural language processing tasks. Sentiment analysis entails information extraction of opinions, emotions, and sentiments. In this paper, we aim to develop and test language models for low-resource language Finnish. We use the term “low-resource” to describe a language lacking in available resources for language modeling, especially annotated data. We investigate four models: the state-of-the-art FinBERT [1], and competitive alternative BERT models Finnish ConvBERT [2], Finnish Electra [3], and Finnish RoBERTa [4]. Having a comparative framework of multiple BERT variations is connected to our use of additional methods …
An Approach for Network Outage Detection from Drive-Testing Databases
2012
A data-mining framework for analyzing a cellular network drive testing database is described in this paper. The presented method is designed to detect sleeping base stations, network outage, and change of the dominance areas in a cognitive and self-organizing manner. The essence of the method is to find similarities between periodical network measurements and previously known outage data. For this purpose, diffusion maps dimensionality reduction and nearest neighbor data classification methods are utilized. The method is cognitive because it requires training data for the outage detection. In addition, the method is autonomous because it uses minimization of drive testing (MDT) functionalit…
How news affect the trading behavior of different categories of investors in a financial market
2015
We investigate the trading behavior of a large set of single investors trading the highly liquid Nokia stock over the period 2003-2008 with the aim of determining the relative role of endogenous and exogenous factors that may affect their behavior. As endogenous factors we consider returns and volatility, whereas the exogenous factors we use are the total daily number of news and a semantic variable based on a sentiment analysis of news. Linear regression and partial correlation analysis of data show that different categories of investors are differently correlated to these factors. Governmental and non profit organizations are weakly sensitive to news and returns or volatility, and, typica…
Health Education Teachers’ Assessment Conceptions and Practices : Identifying Assessment Profiles
2022
The study explored the latent construct underlying the assessment conceptions and practices of Finnish Health Education teachers (n = 165) in the context of curricula, seeking thereby to identify the teachers’ assessment profiles. Six underlying factors were found to encompass their assessment conceptions and practices, namely Assessment supporting learning, Assessment of working, Self and peer assessment as part of grading, Common assessment criteria, Questionable assessment practices, and Norm-referenced assessment. Via cluster analysis, three distinct assessment profiles were identified, labeled as Problematic assessors, Learning supportive assessors, and Norm-based assessors. These find…
Impact of traditional physics lab instruction on students’ critical thinking skills in a Finnish context
2023
Abstract Recent studies have given incentives to physics departments around the world to revise the learning goals of their lab courses to emphasize experimentation skills over reinforcing lecture content. Evaluation instruments have been developed to measure the achievement of learning goals, and one such instrument is the Physics Lab Inventory of Critical thinking (PLIC). The PLIC measures respondents’ ability to evaluate models, evaluate methods, and to suggest the next steps for an investigation. In the present work, we give consideration to the validity of our Finnish translation of the PLIC and we show results from our baseline study of first-year introductory lab courses with labs mi…
Opiskelijoiden verkko-oppimisympäristössä antamat vertaispalautteet tarkastelussa : mitä opittavaa tieteellisen kirjoittamisen ohjaamiselle?
2020
Jyväskylän yliopiston avoimessa yliopistossa on useamman vuoden ajan kehitetty vertaisarviointia ja sen ohjausta osana verkko-opetusta. Olemme jatkaneet vertaispalautetoiminnan kehittämistä tutkimalla, millaista opiskelijoiden kirjoittama vertaispalaute sisällöllisesti on. Kirjoituksessa kuvaamme avoimen yliopiston opiskelijoiden antamien kirjallisten vertaispalautteiden sisältöä ja palautteen muotoa kahdella aineopintotasoisella verkkokurssilla, joissa harjoitellaan tieteellistä kirjoittamista. Pohdimme myös, miten opettajat voisivat ohjata opiskelijoita monipuoliseen palautteenantoon. Luokittelimme opiskelijoiden palautteet evaluaatioihin, muutosehdotuksiin, kysymyksiin ja kommentteihin. …
Prosody and fluency of Finland Swedish as a second language: Investigating global parameters for automated speaking assessment
2023
This study investigates prosody and fluency of Finland Swedish as a second language (L2). The main objective is to investigate global measures of prosody and fluency as predictors of overall oral proficiency, fluency, and pronunciation ratings. We analyzed parameters related to temporal fluency, timing (based on syllable durations), and f0 change from spontaneous speech produced by 30 native and 235 non-native speakers of Finland Swedish representing proficiency levels from beginner to intermediate. We used pairwise comparisons to investigate the differences between native speech (L1) and L2 samples from different proficiency levels. To study the predictability of ratings with acoustic para…
The role of pause location in perceived fluency and proficiency in L2 Finnish
2022
Fluency is a commonly used descriptor of second language (L2) speaking skills. Unplanned and too frequent pauses, hesitations, and repetitions disrupt the flow of speech and can cause temporal irregularities at all levels of speech hierarchy, from syllable rate to phrasing. However, most studies that attempt to quantify fluency disregard pause locations. The current study investigates, whether and which pause locations affect the perceived fluency and proficiency in L2 Finnish. Several pause parameters were computed from spontaneous L2 Finnish speech samples. Pause locations were investigated with regards to clauses and phrases as well as incomplete words. The effect of pause locations to h…
Developing Automated Feedback on Spoken Performance : Exploring the Functioning of Five Analytic Rating Scales Using Many-facet Rasch Measurement
2022
In this study, we used the Many-facet Rasch measurement (MFRM) to explore the quality of ratings as well as the functioning of five analytic rating scales developed for automated assessment of L2 speech. This study is part of a multidisciplinary research project that develops automatic speech recognition (ASR), automated scoring and automated feedback for L2 Finnish and Swedish. The data include the analytic ratings (task completion, fluency, pronunciation, range, accuracy) gathered from human raters (n=14) who assessed L2 Finnish learners’ (n=64) speech samples using Moodle. The four-facet Rasch analysis showed that the raters performed and the rating scales functioned well, although task …
Differences in acoustically determined sentence stress between native and L2 speakers of Finland Swedish
2021
This study describes a pilot attempt to use acoustically determined sentence stress in distinguishing native and L2 speakers of Finland Swedish at different proficiency levels. The study is part of the DigiTala project that examines and develops automatic tools for spoken L2 assessment. Stressed syllables were detected in 235 L2 and 30 L1 speech samples using combinations of f0, intensity, and duration. Differences were found in the relative number of stressed syllables between native and L2 speakers using f0 and duration or all three features. Further research with more consistent speech data is needed to establish reliable automatic measures of sentence stress. nonPeerReviewed