Constructing Hierarchical Product Categories for E-Commerce by Word Embedding and Clustering

Author(s):  
Yi-Hsiang Hsieh ◽  
Shih-Hung Wu ◽  
Liang-Pu Chen ◽  
Ping-Che Yang
2015 ◽  
Author(s):  
Oren Melamud ◽  
Omer Levy ◽  
Ido Dagan

2008 ◽  
Author(s):  
Maria Kaya ◽  
Paul Steffens ◽  
Sönke Albers ◽  
Dennis Proppe

Author(s):  
Sheng Zhang ◽  
Qi Luo ◽  
Yukun Feng ◽  
Ke Ding ◽  
Daniela Gifu ◽  
...  

Background: As a known key phrase extraction algorithm, TextRank is an analogue of PageRank algorithm, which relied heavily on the statistics of term frequency in the manner of co-occurrence analysis. Objective: The frequency-based characteristic made it a neck-bottle for performance enhancement, and various improved TextRank algorithms were proposed in the recent years. Most of improvements incorporated semantic information into key phrase extraction algorithm and achieved improvement. Method: In this research, taking both syntactic and semantic information into consideration, we integrated syntactic tree algorithm and word embedding and put forward an algorithm of Word Embedding and Syntactic Information Algorithm (WESIA), which improved the accuracy of the TextRank algorithm. Results: By applying our method on a self-made test set and a public test set, the result implied that the proposed unsupervised key phrase extraction algorithm outperformed the other algorithms to some extent.


Author(s):  
Dengfeng Yan ◽  
Jaideep Sengupta

Abstract This research seeks to examine, first, whether and why consumers perceive divisible versus indivisible numbers differently and, second, how such divergent perceptions influence consumer preferences for marketer-created entities associated with divisible versus indivisible numbers. Integrating insights from two different literatures—numerical cognition and loneliness—we propose and find that numbers perceived to be divisible (vs. indivisible) are viewed as having more “connections” and are therefore deemed to be less lonely. Building on these findings and the literature on compensatory consumption, we then propose and demonstrate that a temporary feeling of loneliness increases participants’ relative preference for various targets—products, attributes, and prices—associated with divisible (vs. indivisible) numbers, which are perceived to be relatively more connected and less lonely. It merits mention that our findings are triangulated across a wide variety of numbers, different product categories, and multiple operationalizations of loneliness.


Resources ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 72
Author(s):  
Gabriela Jarrín Jácome ◽  
María Fernanda Godoy León ◽  
Rodrigo A. F. Alvarenga ◽  
Jo Dewulf

Aluminium is a metal of high economic importance for the European Union (EU), presenting unique properties (e.g., light weight and high corrosion resistance) and with applications in important sectors (e.g., transportation, construction and packaging). It is also known for its high recyclability potential, but relevant losses occur in its life cycle, compromising the amount of aluminium available for secondary production. A novel methodology that allows the identification of these losses and their impact on the aluminium flows in society is the MaTrace model. The objective of this article is to perform a dMFA of the secondary production of aluminium in the EU technosphere using the modified version of MaTrace, in order to estimate flows of the metal embedded in 12 product categories. Twelve scenarios were built in order to assess the impact of changes in policies, demand and technology. The flows were forecasted for a period of 25 years, starting in 2018. The results of the baseline scenario show that after 25 years, 24% of the initial material remains in use, 4% is hoarded by users, 10% has been exported and 61% has been physically lost. The main contributor to the losses is the non-selective collection of end-of-life products. The results of the different scenarios show that by increasing the collection-to-recycling rates of the 12 product categories, the aluminium that stays in use increase up to 32.8%, reaffirming that one way to keep the material in use is to improve the collection-to-recycling schemes in the EU.


Sign in / Sign up

Export Citation Format

Share Document