Factorizing Historical User Actions for Next-Day Purchase Prediction

It is common practice for many large e-commerce operators to analyze daily logged transaction data to predict customer purchase behavior, which may potentially lead to more effective recommendations and increased sales. Traditional recommendation techniques based on collaborative filtering, although having gained success in video and music recommendation, are not sufficient to fully leverage the diverse information contained in the implicit user behavior on e-commerce platforms. In this article, we analyze user action records in the Alibaba Mobile Recommendation dataset from the Alibaba Tianchi Data Lab, as well as the Retailrocket recommender system dataset from the Retail Rocket website. To estimate the probability that a user will purchase a certain item tomorrow, we propose a new model called Time-decayed Multifaceted Factorizing Personalized Markov Chains (Time-decayed Multifaceted-FPMC), taking into account multiple types of user historical actions not only limited to past purchases but also including various behaviors such as clicks, collects and add-to-carts. Our model also considers the time-decay effect of the influence of past actions. To learn the parameters in the proposed model, we further propose a unified framework named Bayesian Sparse Factorization Machines. It generalizes the theory of traditional Factorization Machines to a more flexible learning structure and trains the Time-decayed Multifaceted-FPMC with the Markov Chain Monte Carlo method. Extensive evaluations based on multiple real-world datasets demonstrate that our proposed approaches significantly outperform various existing purchase recommendation algorithms.

Dynamic Structural Role Node Embedding for User Modeling in Evolving Networks

Complex user behavior, especially in settings such as social media, can be organized as time-evolving networks. Through network embedding, we can extract general-purpose vector representations of these dynamic networks which allow us to analyze them without extensive feature engineering. Prior work has shown how to generate network embeddings while preserving the structural role proximity of nodes. These methods, however, cannot capture the temporal evolution of the structural identity of the nodes in dynamic networks. Other works, on the other hand, have focused on learning microscopic dynamic embeddings. Though these methods can learn node representations over dynamic networks, these representations capture the local context of nodes and do not learn the structural roles of nodes. In this article, we propose a novel method for learning structural node embeddings in discrete-time dynamic networks. Our method, called HR2vec , tracks historical topology information in dynamic networks to learn dynamic structural role embeddings. Through experiments on synthetic and real-world temporal datasets, we show that our method outperforms other well-known methods in tasks where structural equivalence and historical information both play important roles. HR2vec can be used to model dynamic user behavior in any networked setting where users can be represented as nodes. Additionally, we propose a novel method (called network fingerprinting) that uses HR2vec embeddings for modeling whole (or partial) time-evolving networks. We showcase our network fingerprinting method on synthetic and real-world networks. Specifically, we demonstrate how our method can be used for detecting foreign-backed information operations on Twitter.

Jointly Predicting Future Content in Multiple Social Media Sites Based on Multi-task Learning

User-generated contents (UGC) in social media are the direct expression of users’ interests, preferences, and opinions. User behavior prediction based on UGC has increasingly been investigated in recent years. Compared to learning a person’s behavioral patterns in each social media site separately, jointly predicting user behavior in multiple social media sites and complementing each other (cross-site user behavior prediction) can be more accurate. However, cross-site user behavior prediction based on UGC is a challenging task due to the difficulty of cross-site data sampling, the complexity of UGC modeling, and uncertainty of knowledge sharing among different sites. For these problems, we propose a Cross-Site Multi-Task (CSMT) learning method to jointly predict user behavior in multiple social media sites. CSMT mainly derives from the hierarchical attention network and multi-task learning. Using this method, the UGC in each social media site can obtain fine-grained representations in terms of words, topics, posts, hashtags, and time slices as well as the relevances among them, and prediction tasks in different social media sites can be jointly implemented and complement each other. By utilizing two cross-site datasets sampled from Weibo, Douban, Facebook, and Twitter, we validate our method’s superiority on several classification metrics compared with existing related methods.

Does More Context Help? Effects of Context Window and Application Source on Retrieval Performance

We study the effect of contextual information obtained from a user’s digital trace on Web search performance. Contextual information is modeled using Dirichlet–Hawkes processes (DHP) and used in augmenting Web search queries. The context is captured by monitoring all naturally occurring user behavior using continuous 24/7 recordings of the screen and associating the context with the queries issued by the users. We report a field study in which 13 participants installed a screen recording and digital activity monitoring system on their laptops for 14 days, resulting in data on all Web search queries and the associated context data. A query augmentation (QAug) model was built to expand the original query with semantically related terms. The effects of context window and source were determined by training context models with temporally varying context windows and varying application sources. The context models were then utilized to re-rank the QAug model. We evaluate the context models by using the Web document rankings of the original query as a control condition compared against various experimental conditions: (1) a search context condition in which the context was sourced from search history; (2) a non-search context condition in which the context was sourced from all interactions excluding search history; (3) a comprehensive context condition in which the context was sourced from both search and non-search histories; and (4) an application-specific condition in which the context was sourced from interaction histories captured on a specific application type. Our results indicated that incorporating more contextual information significantly improved Web search rankings as measured by the positions of the documents on which users clicked in the search result pages. The effects and importance of different context windows and application sources, along with different query types are analyzed, and their impact on Web search performance is discussed.

Supplier Evaluation and Selection System of Embedded E-Commerce Platform Based on Big Data

For e-commerce companies, it is easier to obtain a large amount of aggregated data about user behavior with the help of embedded network platforms, which contains valuable information that helps to form effective decision-making. This article first gives a detailed introduction to the evaluation and selection of e-commerce and suppliers; then puts forward the analytic hierarchy process and entropy method; finally, the AHP analytic method is used to build a supplier evaluation system and a selection system. The experimental results of this paper show that after obtaining the entropy AHP weights through the analytic hierarchy process, these 8 suppliers can be ranked and selected. Using the ABC classification method, classification is based on the ranking of suppliers. Among them, Class A suppliers account for 12.5%, which plays a key role in the construction of the evaluation and selection system of e-commerce suppliers.

On the Study of Transformers for Query Suggestion

When conducting a search task, users may find it difficult to articulate their need, even more so when the task is complex. To help them complete their search, search engine usually provide query suggestions. A good query suggestion system requires to model user behavior during the search session. In this article, we study multiple Transformer architectures applied to the query suggestion task and compare them with recurrent neural network (RNN)-based models. We experiment Transformer models with different tokenizers, with different Encoders (large pretrained models or fully trained ones), and with two kinds of architectures (flat or hierarchic). We study the performance and the behaviors of these various models, and observe that Transformer-based models outperform RNN-based ones. We show that while the hierarchical architectures exhibit very good performances for query suggestion, the flat models are more suitable for complex and long search tasks. Finally, we investigate the flat models behavior and demonstrate that they indeed learn to recover the hierarchy of a search session.

A Deep Neural Network Model for the Detection and Classification of Emotions from Textual Content

Emotion-based sentimental analysis has recently received a lot of interest, with an emphasis on automated identification of user behavior, such as emotional expressions, based on online social media texts. However, the majority of the prior attempts are based on traditional procedures that are insufficient to provide promising outcomes. In this study, we categorize emotional sentiments by recognizing them in the text. For that purpose, we present a deep learning model, bidirectional long-term short-term memory (BiLSMT), for emotion recognition that takes into account five main emotions (Joy, Sadness, Fear, Shame, Guilt). We use our experimental assessments on the emotion dataset to accomplish the emotion categorization job. The datasets were evaluated and the findings revealed that, when compared to state-of-the-art methodologies, the proposed model can successfully categorize user emotions into several classifications. Finally, we assess the efficacy of our strategy using statistical analysis. This research’s findings help firms to apply best practices in the selection, management, and optimization of policies, services, and product information.

Twitter Engagement in Media Organizations: The Case of the Greek National Broadcasting Corporation

A key parameter in the strategy of news organizations remains the exploitation of factors (such as post time and post type) that enhance the engagement level within online communities on social media. The purpose of this paper is to examine the relationship between post time and post type in correlation with audience response in the Twitter digital platform. Specifically, the study aims to ascertain how the two specific variables affect user engagement with its Twitter posts and how they shape the effectiveness of communication on social networks. The analysis includes 7.122 tweets of the Greek National Broadcasting Corporation (ERT) over four months. Moreover, the study analyzes the tone of user comments on the Twitter posts of the specific public media organizations to understand in-depth how the users communicate their views publicly. The collection of comments lasted seven weeks and they numbered 265 in 2639 tweets. Regarding the post time variable, the study came to important findings on user behavior during the 24 h, as the number of Retweets appears to increase in the morning compared to the afternoon. It was also found that as time goes on, the user is interested in leaving his personal opinion. Regarding the correlation of post type with user engagement, it was found that the accompaniment of a tweet with audiovisual material has a tempting effect on users.

Deep Learning Based Homomorphic Secure Search-Able Encryption for Keyword Search in Blockchain Healthcare System: A Novel Approach to Cryptography

Due to the value and importance of patient health records (PHR), security is the most critical feature of encryption over the Internet. Users that perform keyword searches to gain access to the PHR stored in the database are more susceptible to security risks. Although a blockchain-based healthcare system can guarantee security, present schemes have several flaws. Existing techniques have concentrated exclusively on data storage and have utilized blockchain as a storage database. In this research, we developed a unique deep-learning-based secure search-able blockchain as a distributed database using homomorphic encryption to enable users to securely access data via search. Our suggested study will increasingly include secure key revocation and update policies. An IoT dataset was used in this research to evaluate our suggested access control strategies and compare them to benchmark models. The proposed algorithms are implemented using smart contracts in the hyperledger tool. The suggested strategy is evaluated in comparison to existing ones. Our suggested approach significantly improves security, anonymity, and monitoring of user behavior, resulting in a more efficient blockchain-based IoT system as compared to benchmark models.