Reinard van Dalen
Groningen, Groningen, Netherlands
454 followers
447 connections
About
Marketing and communication - Education - IT - Business - Entrepreneur - Governance - Politics - Skiing
Activity
-
On the move... After an exciting time with Alfa Accountants en Adviseurs, I have joined PwC's Delivering Deal Value team! Alfa is a great…
On the move... After an exciting time with Alfa Accountants en Adviseurs, I have joined PwC's Delivering Deal Value team! Alfa is a great…
Liked by Reinard van Dalen
-
🚀 Vacature Alert: Test Engineer Onderwijsapplicaties 🚀 Ben jij een gepassioneerde Test Engineer met een liefde voor innovatieve…
🚀 Vacature Alert: Test Engineer Onderwijsapplicaties 🚀 Ben jij een gepassioneerde Test Engineer met een liefde voor innovatieve…
Liked by Reinard van Dalen
Experience
-
Rijksuniversiteit Groningen
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Education
Licenses & Certifications
-
MA Information Science
Rijksuniversiteit Groningen
-
BSc Informatiekunde
Rijksuniversiteit Groningen
Publications
-
Hatching Chick at SemEval-2018 Task 2: Multilingual Emoji Prediction
The International Workshop on Semantic Evaluation: Proceedings of the Twelfth Workshop
As part of a SemEval 2018 shared task an attempt was made to build a system capable of predicting the occurence of a language’s most frequently used emoji in Tweets. Specifically, models for English and Spanish data were created and trained on 500.000 and 100.000 tweets respectively. In order to create these models, first a logistic regressor, a sequential LSTM, a random forest regressor and a SVM were tested. The latter was found to perform best and therefore optimized individually for both…
As part of a SemEval 2018 shared task an attempt was made to build a system capable of predicting the occurence of a language’s most frequently used emoji in Tweets. Specifically, models for English and Spanish data were created and trained on 500.000 and 100.000 tweets respectively. In order to create these models, first a logistic regressor, a sequential LSTM, a random forest regressor and a SVM were tested. The latter was found to perform best and therefore optimized individually for both languages. During developmet f1-scores of 61 and 82 were obtained for English and Spanish data respectively, in comparison, f1-scores on the official evaluation data were 21 and 18. The significant decrease in performance during evaluation might be explained by overfitting during development and might therefore have partially be prevented by using cross-validation. Over all, emoji which occur in a very specific context such as a Christmas tree were found to be most predictable.
-
Profiling Dutch Authors on Twitter: Discovering Political Preference and Income Level
Computational Linguistics in the Netherlands Journal
Research in author profiling has primarily focused on English-speaking users and attributes like age, gender and occupation. We present first experiments on automatic profiling Dutch Twitter users for two less-studied attributes, namely their political preference and income level (low vs high). We create two novel corpora using distant supervision, evaluate the corpus creation approach, and train predictive models for each attribute. Our empirical evaluation shows that distant supervision is…
Research in author profiling has primarily focused on English-speaking users and attributes like age, gender and occupation. We present first experiments on automatic profiling Dutch Twitter users for two less-studied attributes, namely their political preference and income level (low vs high). We create two novel corpora using distant supervision, evaluate the corpus creation approach, and train predictive models for each attribute. Our empirical evaluation shows that distant supervision is surprisingly reliable and political preference and income level of Dutch users can be predicted relatively accurately from the linguistic input. We also discuss which features are predictive for income and political preference, respectively.
Languages
-
Nederlands
Native or bilingual proficiency
-
Engels
-
-
Duits
-
More activity by Reinard
How do international newspapers report on climate change? 📰 The paper Marc Esteve Del Valle, Malvina Nissim and I just published in PLOS ONE…
Liked by Reinard van Dalen
Een bijzondere week, want vanaf nu ben ik weer fulltime ondernemer, gespecialiseerd in Generative AI en ChatGPT trainingen! Na 3 jaar met veel…
Liked by Reinard van Dalen
Wil jij werken in een jong en dynamisch team en ook echt je steentje bijdragen aan het onderwijs van onze studenten? Kijk dan eens op onze "werken…
Liked by Reinard van Dalen
Tijd voor een nieuwe uitdaging! 🙌 Zeven jaar geleden begonnen we te ondernemen met Flocker, en bijna vijf jaar geleden gaf ik voor het eerst…
Liked by Reinard van Dalen
Ben jij of ken jij een student aan de RUG die toe is aan de volgende stap? Ons Edusupport team zoekt nieuwe collega's voor de ondersteuning van alle…
Liked by Reinard van Dalen
De RUG is per 1 Mei 2024 op zoek naar: Enthousiaste EDU Supporter voor 12 uur per week. Wil jij een actieve rol spelen in het optimaliseren van de…
Liked by Reinard van Dalen
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More