Chen Ziyang, Gurdian Cristhiam, Sharma Chetan, Prinyawiwatkul Witoon, Torrico Damir D
Centre of Excellence-Food for Future Consumers, Department of Wine, Food and Molecular Biosciences, Faculty of Agriculture and Life Sciences, Lincoln University, Lincoln 7647, New Zealand.
Agricultural Center, School of Nutrition and Food Sciences, Louisiana State University, Baton Rouge, LA 70803, USA.
Foods. 2021 Oct 21;10(11):2537. doi: 10.3390/foods10112537.
Increased meat consumption has been associated with the overuse of fresh water, underground water contamination, land degradation, and negative animal welfare. To mitigate these problems, replacing animal meat products with alternatives such as plant-, insect-, algae-, or yeast-fermented-based proteins, and/or cultured meat, is a viable strategy. Nowadays, there is a vast amount of information regarding consumers' perceptions of alternative proteins in scientific outlets. Sorting and arranging this information can be time-consuming. To overcome this drawback, text mining and Natural Language Processing (NLP) are introduced as novel approaches to obtain sensory data and rapidly identify current consumer trends. In this study, the application of text mining and NLP in gathering information about alternative proteins was explored by analyzing key descriptive words and sentiments from = 20 academic papers. From 2018 to 2021, insect- and plant-based proteins were the centers of alternative proteins research as these were the most popular topics in current studies. Pea has become the most common source for plant-based protein applications, while spirulina is the most popular algae-based protein. The emotional profile analysis showed that there was no significant association between emotions and protein categories. Our work showed that applying text mining and NLP could be useful to identify research trends in recent sensory studies. This technique can rapidly obtain and analyze a large amount of data, thus overcoming the time-consuming drawback of traditional sensory techniques.
肉类消费的增加与淡水过度使用、地下水污染、土地退化以及负面动物福利相关联。为缓解这些问题，用植物、昆虫、藻类或酵母发酵蛋白等替代品以及/或培养肉来替代动物肉制品，是一种可行的策略。如今，在科学渠道中有大量关于消费者对替代蛋白看法的信息。整理和排列这些信息可能很耗时。为克服这一缺点，文本挖掘和自然语言处理（NLP）作为获取感官数据并快速识别当前消费者趋势的新方法被引入。在本研究中，通过分析20篇学术论文中的关键描述性词汇和情感倾向，探讨了文本挖掘和NLP在收集替代蛋白信息方面的应用。从2018年到2021年，昆虫蛋白和植物蛋白是替代蛋白研究的核心，因为它们是当前研究中最热门的话题。豌豆已成为植物蛋白应用中最常见的来源，而螺旋藻是最受欢迎的藻类蛋白。情感特征分析表明，情感与蛋白类别之间没有显著关联。我们的工作表明，应用文本挖掘和NLP有助于识别近期感官研究中的研究趋势。该技术可以快速获取和分析大量数据，从而克服传统感官技术耗时的缺点。
