TUTORIAL: AI research without coding: The art of fighting without fighting: Data science for qualitative researchers
آموزش: تحقیقات هوش مصنوعی بدون رمزگذاری: هنر مبارزه بدون جنگ: علم داده برای محققان کیفی-2020
In this tutorial, we show how to scrape and collect online data, perform sentiment analysis, social network analysis, tribe finding, and Wikidata cross-checks, all without using a single line of programming code. In a stepby- step example, we use self-collected data to perform several analyses of the glass ceiling. Our tutorial can serve as a standalone introduction to data science for qualitative researchers and business researchers, who have avoided learning to program. It should also be useful for experienced data scientists who want to learn about the tools that will allow them to collect and analyze data more easily and effectively.
Keywords: Twitter | Data scraping | Sentiment analysis | Tribe finding | Wikidata
Bridging the gap between linked open data-based recommender systems and distributed representations
ایجاد شکاف بین سیستمهای پیشنهادی مبتنی بر داده باز و پیوندهای داده شده توزیع شده-2019
Recently, several methods have been proposed for introducing Linked Open Data (LOD) into recommender systems. LOD can be used to enrich the representation of items by leveraging RDF statements and adopting graph-based methods to implement effective recommender systems. However, most of those methods do not exploit embeddings of entities and relations built on knowledge graphs, such as datasets coming from the LOD. In this paper, we propose a novel recommender system based on holographic embeddings of knowledge graphs built from Wikidata, a free and open knowledge base that can be read and edited by both humans and machines. The evaluation performed on three standard datasets such as Movielens 1M, Last.fm and LibraryThing shows promising results, which confirm the effectiveness of the proposed method.
Keywords: Recommender systems | Knowledge graph embedding | Linked data