Enriching Topic Coherence on Reviews for Cross-Domain Recommendation

2020 ◽  
Author(s):  
Mala Saraswat ◽  
Shampa Chakraverty

Abstract With the advent of e-commerce sites and social media, users express their preferences and tastes freely through user-generated content such as reviews and comments. In order to promote cross-selling, e-commerce sites such as eBay and Amazon regularly use such inputs from multiple domains and suggest items with which users may be interested. In this paper, we propose a topic coherence-based cross-domain recommender model. The core concept is to use topic modeling to extract topics from user-generated content such as reviews and combine them with reliable semantic coherence techniques to link different domains, using Wikipedia as a reference corpus. We experiment with different topic coherence methods such as pointwise mutual information (PMI) and explicit semantic analysis (ESA). Experimental results presented demonstrate that our approach, using PMI as topic coherence, yields 22.6% and using ESA yields 54.4% higher precision as compared with cross-domain recommender system based on semantic clustering.

2020 ◽  
Vol 54 (8) ◽  
pp. 1963-1986
Author(s):  
Tilottama G. Chowdhury ◽  
Feisal Murshed

Purpose This paper proposes that categorization flexibility, operationalized as the cognitive capacity that cross-categorizes products in multiple situational categories across multiple domains, might favorably influence a consumer’s evaluation of unconventional options. Design/methodology/approach Experimental research design is used to test the theory. An exploratory study first establishes the effect of categorization flexibility in a non-food domain. Study 1 documents the moderating role of decision domain, showing that the effect works only under low- (vs high-) consequence domain. Studies 2A and 2B further refine the notion by showing that individuals can be primed in a relatively higher categorization flexibility frame of mind. Study 3 demonstrates the interactive effect of categorization flexibility and adventure priming in a high-consequence domain. Study 4 integrates the interactive effects of decisions with low- vs high-consequence, adventure priming and categorization flexibility within a single decision domain of high consequence. Findings Consumers with higher- (vs lower-) categorization flexibility tend to opt for unconventional choices when the decision domain entails low consequences, whereas such a result does not hold under decision domain of high consequences. The categorization flexibility effects in case of low-consequence decision domain holds true even when consumers are primed to be categorization flexible. Furthermore, with additional adventure priming, consumers show an increased preference for unconventional options even under a decision domain with high consequence. Research limitations/implications This study could not examine real purchase behavior as results are based on cross-sectional, behavioral intention data. In addition, it did not examine the underlying reason for presence of cross-domain categorization flexibility index. Practical implications The results suggest that stimuli may be tailored to consumers in ways that increase the salience and the perceived attractiveness of unconventional choices. Further, data reinforce the notion of cross-categorical interrelations among different domains, which could be leveraged by marketers. Originality/value This study represents the first documentation of the potential ways by which unconventional product choice might be a function of individuals’ categorization flexibility level across different types of decision domains. The findings yield implications that are novel to both categorization and consumer decision-making literature.


Author(s):  
Tiffany Renteria-Vazquez ◽  
Warren S. Brown ◽  
Christine Kang ◽  
Mark Graves ◽  
Fulvia Castelli ◽  
...  

2018 ◽  
Vol 4 ◽  
Author(s):  
Faez Ahmed ◽  
Mark Fuge

Bisociative knowledge discovery is an approach that combines elements from two or more ‘incompatible’ domains to generate creative solutions and insight. Inspired by Koestler’s notion of bisociation, in this paper we propose a computational framework for the discovery of new connections between domains to promote creative discovery and inspiration in design. Specifically, we propose using topic models on a large collection of unstructured text ideas from multiple domains to discover creative sources of inspiration. We use these topics to generate a Bisociative Information Network – a graph that captures conceptual similarity between ideas – that helps designers find creative links within that network. Using a dataset of thousands of ideas from OpenIDEO, an online collaborative community, our results show usefulness of representing conceptual bridges through collections of words (topics) in finding cross-domain inspiration. We show that the discovered links between domains, whether presented on their own or via ideas they inspired, are perceived to be more novel and can also be used as creative stimuli for new idea generation.


Information ◽  
2020 ◽  
Vol 11 (11) ◽  
pp. 535 ◽  
Author(s):  
Alejandro Ramón-Hernández ◽  
Alfredo Simón-Cuevas ◽  
María Matilde García Lorenzo ◽  
Leticia Arco ◽  
Jesús Serrano-Guerrero

Opinion mining and summarization of the increasing user-generated content on different digital platforms (e.g., news platforms) are playing significant roles in the success of government programs and initiatives in digital governance, from extracting and analyzing citizen’s sentiments for decision-making. Opinion mining provides the sentiment from contents, whereas summarization aims to condense the most relevant information. However, most of the reported opinion summarization methods are conceived to obtain generic summaries, and the context that originates the opinions (e.g., the news) has not usually been considered. In this paper, we present a context-aware opinion summarization model for monitoring the generated opinions from news. In this approach, the topic modeling and the news content are combined to determine the “importance” of opinionated sentences. The effectiveness of different developed settings of our model was evaluated through several experiments carried out over Spanish news and opinions collected from a real news platform. The obtained results show that our model can generate opinion summaries focused on essential aspects of the news, as well as cover the main topics in the opinionated texts well. The integration of term clustering, word embeddings, and the similarity-based sentence-to-news scoring turned out the more promising and effective setting of our model.


2011 ◽  
Vol 29 (2) ◽  
pp. 1-34 ◽  
Author(s):  
Ofer Egozi ◽  
Shaul Markovitch ◽  
Evgeniy Gabrilovich

Sign in / Sign up

Export Citation Format

Share Document