← Return to program

Cultural and Linguistic Influences on Translation: A Study of Novels

Saturday 2:10 PM–2:40 PM in Eureka 2

How do translations preserve the original meaning, style, and sentiment of texts across different languages and cultural contexts? This intriguing question drives our study as we delve into the complexities of translation.

We examine how sentiment analysis results differ for the same text in various languages, aiming to understand the role of language families in these variations. Using natural language processing techniques in Python, we analyse novels from diverse genres, time periods, and cultural backgrounds to uncover generalisable translation patterns.

Our study seeks to answer whether translations of words, ideas, and societal contexts in novels are influenced by the cultural contexts into which they are translated. By highlighting the importance of accurate and culturally relevant translations, we emphasise how they play a crucial role in preserving cultural and societal knowledge, ensuring that the richness of the original text is maintained across languages.

See this talk and many more by getting your ticket to PyCon AU now!

I want a ticket!

Our project aims to find out how closely translations preserve the original meaning and style of text, whether the sentiment expressed in the original text is consistently preserved across different translations, and how sentiment analysis results vary for the same text in different languages.

As such, we have chosen novels based on different genres and societies, so that we can analyse words in various contexts. We have also chosen our novels based on the languages we are analysing, making sure we include books that are originally written by both languages and other languages.

In this project, we created several study groups of languages. For instance, we might put English with Mandarin Chinese together, so that we can analyse different language families. In each language group, we will assign source and target language, and find the translation patterns within the group. To generalise translation patterns, we repeated the analyses on multiple books and across multiple language groups. Then, we applied feature extraction to extract semantic, stylistic, syntactic and sentiment features from translations of novels. And lastly, to apply sentiment preservation by applying sentiment analysis and comparative semantic analysis to generalise language features in translation.

This project is important to us because we are both students from multilingual backgrounds and interact with translations every day. We realised that the same articles translated into different languages may not necessarily bring out the same ideologies or sentiments. Therefore, we are interested in how translation of a text will vary in different contexts, and whether the language family plays a big role in this. We believe this project is important as it can impact how one would understand particular historical, cultural or societal knowledge of a community if not done well.

We considered the differences in translation styles when translated by different authors, as well as different editing styles. To conquer this, we analysed works from different authors and translators to minimise the impact of stylistic differences.

Anneysha Sarkar

Hi, I am Anneysha, I am studying Advanced Computing at the Australian National University. I love languages, and learning as many language scripts as I can!

I am interested in solving problems using a human-centric approach with strong backing from existing data and applying computational techniques to it, such as Natural Language Processing, and Machine Learning. In my free time, I like watching anime, cooking (things I’ve never made before!), and travelling.

Eliz So

I’m Eliz, a student from Australian National University (ANU) studying a double degree in Politics, Philosophy and Economics and Science (majoring in Computer Science and minoring in Mathematics). I have been fascinated by how computing works since young, and decided to learn programming then! In my free time I enjoy creating 3D models, photography and videography, playing music and bouldering. I’m looking forward to putting my computing skills in my hobbies as well, such as integrating computer vision with photography and videography. In the meantime, I would love to learn more about different aspects in machine learning and theoretical computing.