Music plays a crucial role in children’s development by helping them express their identity, teaching them to belong to a culture, and developing their cognitive well-being and inner self-worth. Most music nowadays is consumed through online streaming websites like Spotify, which make use of recommendation systems to suggest new tracks. These recommendation algorithms internally make use of user and song features that aid in making predictions. However, as most of the research literature focuses on making recommendations for the adult group, few studies explore what makes the recommended songs appealing to children. In this paper, we perform user modelling techniques on the listening history of the children combined with high-level descriptors of the songs in order to capture their music preferences. By constructing user profiles, we aim to identify the characteristics of music that resonate most with the listener. In our research, we focus on children belonging to the age group of 6-17 years. The goal is to aid
in the design of future recommender systems that operate with greater transparency, allowing the impact of the user choices to be clearly observed by the consumer.

In this paper, we aim to uncover previously unknown relationships between readability and phoneme-related features of text. Phonemes are the smallest unit of sound that can distinguish one word from another. Phonemes encode pronunciation, therefore they encode phonetic/auditory details about words that letters do not capture. However, the use of phonemes to aid readability estimation has thus far been limited in literature. This paper aims to bridge this knowledge gap by investigating the relationship between readability and individual phonemes, groupings of phonemes, and phoneme-derived features. The experiments are carried out on the WeeBit corpus. Our findings indicate that phoneme-related properties on their own do not serve as accurate indicators of text complexity.

Investigating changes in forest cover has been an area of intense research for decades. From manual surveys to remote sensing we have come a long way in mapping the world around us. Machine learning and its' younger sibling, deep learning, have emerged as highly useful tools on this journey. There are a wide variety of algorithms that take a stab at analysing vegetation coverage, but not all of them are easily accessible to the community at large. This was the underlying incentive for the paper you are about to read - reproducing and replicating a novel deep-learning algorithm that generates maps of forest cover in a relatively under-explored part of the world. This study lays out the methodology devised by the original authors as well as our attempts to replicate their work on a different set of data. We present the results we were able to obtain, the hurdles we encountered along the way, and a set of guidelines we feel would be helpful for future researchers.