scholarly journals Mixed Information Flow for Cross-Domain Sequential Recommendations

2022 ◽  
Vol 16 (4) ◽  
pp. 1-32
Author(s):  
Muyang Ma ◽  
Pengjie Ren ◽  
Zhumin Chen ◽  
Zhaochun Ren ◽  
Lifan Zhao ◽  
...  
Keyword(s):  
Information Flow ◽  
Sequential Behavior ◽  
Flow Network ◽  
Cross Domain ◽  
Transfer Unit ◽  
Sequence Representation ◽  
Multiple Domains ◽  
Flow Of Information ◽  
Domain Information ◽  
Behavioral Information

Cross-domain sequential recommendation is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One of the key challenges in cross-domain sequential recommendation is to grasp and transfer the flow of information from multiple domains so as to promote recommendations in all domains. Previous studies have investigated the flow of behavioral information by exploring the connection between items from different domains. The flow of knowledge (i.e., the connection between knowledge from different domains) has so far been neglected. In this article, we propose a mixed information flow network for cross-domain sequential recommendation to consider both the flow of behavioral information and the flow of knowledge by incorporating a behavior transfer unit and a knowledge transfer unit . The proposed mixed information flow network is able to decide when cross-domain information should be used and, if so, which cross-domain information should be used to enrich the sequence representation according to users’ current preferences. Extensive experiments conducted on four e-commerce datasets demonstrate that the proposed mixed information flow network is able to improve recommendation performance in different domains by modeling mixed information flow. In this article, we focus on the application of mixed information flow network s to a scenario with two domains, but the method can easily be extended to multiple domains.

Categorization flexibility and unconventional choices: is life an adventure?

2020 ◽  
Vol 54 (8) ◽  
pp. 1963-1986
Author(s):  
Tilottama G. Chowdhury ◽  
Feisal Murshed
Keyword(s):  
Interactive Effect ◽  
Interactive Effects ◽  
Cognitive Capacity ◽  
Purchase Behavior ◽  
Consumer Decision Making ◽  
Cross Sectional ◽  
Content Type ◽  
Cross Domain ◽  
Multiple Domains

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.

Dynamic cross domain information sharing

2010 ◽  
Author(s):  
Michael Atighetchi ◽  
Jonathan Webb ◽  
Partha Pal ◽  
Joseph Loyall ◽  
Azer Bestavros ◽  
...  
Keyword(s):  
Information Sharing ◽  
Cross Domain ◽  
Domain Information

scholarly journals Creative exploration using topic-based bisociative networks

2018 ◽  
Vol 4 ◽  
Author(s):  
Faez Ahmed ◽  
Mark Fuge
Keyword(s):  
Idea Generation ◽  
Information Network ◽  
Large Collection ◽  
Computational Framework ◽  
Conceptual Similarity ◽  
Cross Domain ◽  
Unstructured Text ◽  
Collaborative Community ◽  
Creative Solutions ◽  
Multiple Domains

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.

SMS as a Tool to Improve Information Flow on Humanitarian Logistics

2019 ◽  
pp. 408-422
Author(s):  
Vanesa A. Alcantara Panta ◽  
Sandra E. Zambrano Hinojoza ◽  
Amelia A. Flores Dextre ◽  
Andrea Guillen Reina ◽  
Brenda Pedreschi Garcia
Keyword(s):  
Mobile Phone ◽  
Information Flow ◽  
Rapid Assessment ◽  
Humanitarian Logistics ◽  
Mobile Phone Technology ◽  
Humanitarian Operations ◽  
The People ◽  
Assessment Visit ◽  
Flow Through ◽  
Flow Of Information

This chapter assesses the suitability of mobile phone technology, an established technology (humanitarian), to support humanitarian operations, create an inventory of support donations, and track the needs of people throughout humanitarian logistics after the disaster. The main objective is to reduce the exposure to the consequences of disasters by reducing the time of information flow through SMS interaction technology. Quebrada Quirio was used as a prototype. The process consists of using the INDECI rapid assessment visit to collect basic data, including a telephone number, of the people affected by the disaster, and based on this information, multiple initiatives aligned with the optimization of the flow of information were created.

Influence and Information Flow in Online Social Networks

2021 ◽  
pp. 502-520
Author(s):  
Afrand Agah ◽  
Mehran Asadi
Keyword(s):  
Social Networks ◽  
Information Flow ◽  
Online Social Networks ◽  
Large Data ◽  
Marketing Strategies ◽  
Divide And Conquer ◽  
Data Sets ◽  
Divide And Conquer Algorithm ◽  
Flow Of Information

This article introduces a new method to discover the role of influential people in online social networks and presents an algorithm that recognizes influential users to reach a target in the network, in order to provide a strategic advantage for organizations to direct the scope of their digital marketing strategies. Social links among friends play an important role in dictating their behavior in online social networks, these social links determine the flow of information in form of wall posts via shares, likes, re-tweets, mentions, etc., which determines the influence of a node. This article initially identities the correlated nodes in large data sets using customized divide-and-conquer algorithm and then measures the influence of each of these nodes using a linear function. Furthermore, the empirical results show that users who have the highest influence are those whose total number of friends are closer to the total number of friends of each node divided by the total number of nodes in the network.

Enriching Topic Coherence on Reviews for Cross-Domain Recommendation

2020 ◽  
Author(s):  
Mala Saraswat ◽  
Shampa Chakraverty
Keyword(s):  
Topic Modeling ◽  
Semantic Analysis ◽  
User Generated Content ◽  
Core Concept ◽  
Semantic Clustering ◽  
Cross Domain ◽  
Semantic Coherence ◽  
Reference Corpus ◽  
Multiple Domains ◽  
Explicit Semantic Analysis

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.

Sign in / Sign up

Export Citation Format

Share Document