User Purchase Research Articles

The influence of UGC features on consumers' purchase intention in social e-commerce platforms: Taking Xiaohongshu as an example

With the rapid development of social e-commerce, content-based social e-commerce platforms have become one of the main channels for consumers to obtain information. And this social e-commerce platform relies on user generated content to convey valuable information to users. The relationship between user generated content and user purchase intention is still a question worth exploring. This article starts from an empirical perspective and studies the mediating variables between UGC text features and consumer purchase intention in social e-commerce platforms. Based on speech act theory (SAT) and receptor stimulus response theory (SOR), research hypotheses are proposed, with perceived value, perceived risk, and perceived interest as mediating variables. By using AMOS to construct a structural effects equation for verification, it is concluded that UGC text features can positively affect perceived value, perceived risk, perceived interest, and have an effective impact on purchase intention.

Intelligent Recommendation Algorithm for Product Information on E-commerce Platforms Based on Robot Customer Service Automatic Q&A

In order to enhance the shopping experience of customers and retain them, thereby increasing sales volume, the author proposes the research topic of an intelligent recommendation system for product information on e-commerce platforms based on robot customer service automatic question answering. Firstly, starting directly from the question itself, the system can provide feedback to customers by simply segmenting the questions submitted by customers and matching them with semantic templates; Secondly, the system automatically builds and updates the user’s personalized knowledge base, using this to predict user purchasing tendencies and achieve the function of recommending products to customers. The implementation of the intelligent shopping robot system has passed 365 question and answer tests on 5G mobile phone sales terms, and is feasible in the professional field. The experimental results indicate that, when the number of training corpora increased to 300, the accuracy of the system was 0.85, 0.90, and 0.98 using 100, 2003, and 300 tests respectively. Such a system is perfect for natural language processing, so we can improve the system by expanding and improving the knowledge base. The intelligent shopping robot recommendation system studied by the author is still in the analysis and demonstration stage, sincerely hope that the processing method used in this project can have reference significance for similar recommendation systems in the near future.

Fusing temporal and semantic dependencies for session-based recommendation

Session-based recommendation (SBR) predicts the next item in user sequences. Existing research focuses on item transition patterns, neglecting semantic information dependencies crucial for understanding users’ preferences. Incorporating semantic characteristics is vital for accurate recommendations, especially in applications like user purchase sequences. In this paper, to tackle the above issue, we novelly propose a framework that hierarchically fuses temporal and semantic dependencies. Technically, we present the Item Transition Dependency Module and Semantic Dependency Module based on the whole session set: (i) Item Transition Dependency Module is exclusively to learn the item embeddings through temporal relations and utilizes item transitions from both global and local levels; (ii) Semantic Dependency Module develops mutually independent embeddings of both sessions and items via stable interaction relations. In addition, under the unified organization of the Cross View, semantic information is adaptively incorporated into the temporal dependency learning and used to improve the performance of SBR. Extensive experiments on three large-scale real-world datasets show the superiority of our framework over current state-of-the-art methods. In particular, our model improves its performance over SOTA on all three datasets, with 5.5%, 0.2%, and 3.0% improvements on Recall@20, and 5.8%, 4.6%, and 2.0% improvements on MRR@20, respectively.

The Influence of User Experience on Decisions PLN Mobile User Purchases

This study aims to reveal the influence of user experience (UX) quality on purchasing decisions in the PLN Mobile application. Using a quantitative approach, this study analyzes data obtained from 97 active users of PLN Mobile. Data was collected through questionnaires distributed to users who met the criteria of having previously made transactions in the application. The sampling technique used was purposive sampling. The results of simple linear regression analysis show a very significant and positive relationship between the UX variable and purchasing decisions. It was found that 72.1% of the variation in purchasing decisions can be explained by the UX variable. This finding indicates that the better the user experience, the more likely users are to make purchases through the PLN Mobile application. Thus, this study emphasizes the importance of the role of UX in driving purchasing decisions in public service applications such as PLN Mobile. By taking PLN Mobile as the subject of the study, this study provides a new perspective on the importance of UX in the context of public service applications.

The Study on the Influencing Factors of Consumer Purchase Intention in Live-Streaming Sales

This study focuses on the influencing factors of user purchase intention in e-commerce live streaming. Based on the SOR theory model, a research model is constructed from the perspective of consumer perception. The results show that the popularity, professionalism, and homogeneity of e-commerce streamers, as well as the price discounts and content quality in e-commerce live streaming product features, and the spatial and social presence in e-commerce live streaming presence features, can directly and positively affect users' purchase intention. At the same time, they can significantly and positively affect perceived value, and perceived value has a significant indirect mediating effect between e-commerce live streaming features and users' purchase intention.

Understanding the effect of TikTok marketing on user purchase behavior: a mixed-methods approach

Understanding the effect of TikTok marketing on user purchase behavior: a mixed-methods approach

CF-MGAN: Collaborative filtering with metadata-aware generative adversarial networks for top-N recommendation

Generative Adversarial Networks (GANs) have several advantages over latent variable and autoregressive models, such as directly computing the input data distribution, fast sampling, and best samples generated. Furthermore, the metadata information of users and items plays a crucial role in effectively learning the user-item latent representations. Existing neural network approaches are deterministic, incapable of accounting for user-item latent representations, and the rating prediction process is calculative rather than generative. However, only some papers have utilized GANs for information retrieval tasks. However, they have several limitations, such as the inability to abstract data effectively, the limitation of the model's ability to learn accurate latent representations, and the absence of metadata information. To address these issues, we propose a GAN-based recommendation framework named Collaborative Filtering with Metadata-awareGenerative Adversarial Networks (CF-MGAN) to learn complex rating distribution for collaborative filtering (CF) tasks. We use a negative item generator for the implicit user purchase vector to prevent GAN from generating biased ratings. We exploited metadata information to overcome data sparsity issues. We use Variational Autoencoder to abstract user-item metadata features, a regularizer for GAN-generated rating. Extensive experiments on datasets reveal the effectiveness of the proposed model, showing an improvement in the top-N recommendation task.

The INFORMATION SYSTEMS PERSPECTIVE: THE IMPACT OF USER INTERFACE ON CONSUMER PURCHASE INTENTIONS BASED ON A SYSTEMATIC REVIEW OF USER EXPERIENCE

Shopee is one of the largest online marketplaces in Indonesia that conducts the buying and selling process through mobile phones and adopts the concept of social media shopping. As the number of Shopee users increases, the challenges and problems increase, as does the quality of service and system accuracy. User interface (UI) plays an important role in shaping user purchase intent. Various previous studies have studied and identified user interface factors that affect Shopee consumer satisfaction, but there is still more information that can be utilized towards comprehensively understanding and analyzing the trends in UI evaluation methods used, as well as trends in UI factors that affect consumer satisfaction, and factors that affect Shopee consumers' purchase intention. Thus, a systematic review of the literature is needed. A total of 120 peer-reviewed research studies were conducted on the research topic of the impact of user interface on shopee application satisfaction published between 2019-2023 and extracted 30 relevant articles from the discussion of inclusion and exclusion criteria. The results of this study found that service quality is the main factor compared to advertisements and free shipping used in evaluating shopee, and user-friendly factors are in the main position that affects the purchase intention of the shopee application. This study provides further research topics that need to be studied further regarding advertising and free shipping in influencing consumer purchase intention seen from the UI on the shopee application.

Hierarchical representation learning for next basket recommendation

The task of next basket recommendation is pivotal for recommender systems. It involves predicting user actions, such as the next product purchase or movie selection, by exploring sequential purchase behavior and integrating users’ general preferences. These elements may converge and influence users’ subsequent choices. The challenge intensifies with the presence of varied user purchase sequences in the training set, as indiscriminate incorporation of these sequences can introduce superfluous noise. In response to these challenges, we propose an innovative approach: the Selective Hierarchical Representation Model (SHRM). This model effectively integrates transactional data and user profiles to discern both sequential purchase transactions and general user preferences. The SHRM’s adaptability, particularly in employing nonlinear aggregation operations on user representations, enables it to model complex interactions among various influencing factors. Notably, the SHRM employs a Recurrent Neural Network (RNN) to capture extended dependencies in recent purchasing activities. Moreover, it incorporates an innovative sequence similarity task, grounded in a k-plet sampling strategy. This strategy clusters similar sequences, significantly mitigating the learning process’s noise impact. Through empirical validation on three diverse real-world datasets, we demonstrate that our model consistently surpasses leading benchmarks across various evaluation metrics, establishing a new standard in next-basket recommendation.

An Exploration of the Development of Computerized Data Mining Techniques and Their Application

The process of data mining involves extracting valuable information and knowledge from vast amounts of data, encompassing various fields such as statistics, machine learning, and database theory. It transcends mere data processing tools, employing intelligent methods for data analysis and stands as a pivotal technology in the era of big data. Its applications span across numerous domains including consumer behavior analysis, market marketing strategies, risk management, medical diagnosis, and fraud detection, with notable prominence in the realm of commerce. In e-commerce platforms, data mining techniques adeptly analyze user purchase histories and browsing records to precisely identify user preferences, recommend personalized products, thus enhancing user satisfaction and sales revenue. In devising marketing strategies, analyzing market data and consumer feedback optimizes product promotion strategies, bolstering market competitiveness. In the medical domain, data mining exhibits robust vitality. By analyzing patient medical records, genetic data, drug response data, predictions of disease trends, optimization of treatment plans, and even early disease warnings are made possible, thereby improving disease cure rates. In the realm of financial security, data mining plays a pivotal role by analyzing transaction data and user behavior to timely detect abnormal transactions and identify fraudulent activities, thereby safeguarding the security and stability of the financial system. In the Internet of Things (IoT) domain, data mining techniques analyze massive sensor data, enabling real-time monitoring and predictive maintenance of devices, thus enhancing operational efficiency and longevity. Data mining extends beyond the aforementioned domains, finding significant applications in social governance, scientific research, intelligent manufacturing, and more. Not only does data mining enhance the scientific rigor and precision of decision-making, but it also empowers various industries to improve efficiency, realize intelligent transformations, thereby further advancing societal progress.

Pengaruh Daya Tarik Iklan, Citra Merek, dan Persepsi Harga Terhadap Minat Beli Layanan Netflix Covid-19

The Covid-19 pandemic, which began in 2020, has altered societal behavior patterns, including an increased reliance on online streaming services such as Netflix. This article analyzes the pandemic's impact on Netflix's services and the factors influencing post-pandemic user purchase intent. Through data and news quotations, this article highlights the significant growth of new Netflix users during the pandemic and the company's response to increased demand. Additionally, previous research on advertising appeal, brand image, and price perception is examined to understand how these factors affect user purchase intent. The research findings indicate that purchase decisions significantly influence user purchase intent for Netflix services. This finding is consistent with previous studies emphasizing the crucial role of advertising appeal in influencing purchase intent. Furthermore, a positive brand image has been proven to increase user purchase intent. However, in the context of price perception, no significant impact on purchase intent was found, underscoring that price does not significantly affect online customer purchase intent. In conclusion, to enhance user purchase intent and decision-making, it is important to consider advertising appeal and brand image aspects in Netflix's marketing strategy.

Does similarity matter? Investigating the relationship between live streamer' communication style similarity and user purchase intentions during live streaming

This study investigates the influence of communication style similarity between streamers and viewers on purchase intention within the framework of similarity attraction theory and cognitive-emotional system theory. Live marketing, utilizing online streamers for real-time interaction with consumers, has become a prominent sales strategy. A quantitative approach was employed, using questionnaire data collected from live marketing audiences. The survey measured communication style preferences of both viewers and streamers, along with viewers' perceived level of quasi-social interaction during the live stream, immersive experience, and purchase intention. The research demonstrates that when a streamer's communication style aligns with a viewer's preference, viewers perceive a stronger sense of quasi-social interaction. This heightened sense of connection fosters a more immersive live streaming experience, ultimately leading to a greater purchase intention. Furthermore, the study reveals that viewers with a higher need for cognitive closure-the desire to minimize ambiguity-experience an amplified effect of both communication style similarity and immersive experience on their purchase intention. This research contributes to the evolving body of knowledge on live marketing communication. By highlighting the importance of communication style matching between streamers and viewers, the findings offer valuable guidance to live streaming platforms and companies. Tailoring streamer communication styles to align with target audience preferences can enhance audience engagement, create a more immersive experience, and ultimately drive higher conversion rates.

Preference Aware Dual Contrastive Learning for Item Cold-Start Recommendation

Existing cold-start recommendation methods often adopt item-level alignment strategies to align the content feature and the collaborative feature of warm items for model training, however, cold items in the test stage have no historical interactions with users to obtain the collaborative feature. These existing models ignore the aforementioned condition of cold items in the training stage, resulting in the performance limitation. In this paper, we propose a preference aware dual contrastive learning based recommendation model (PAD-CLRec), where the user preference is explored to take into account the condition of cold items for feature alignment. Here, the user preference is obtained by aggregating a group of collaborative feature of the warm items in the user's purchase records. Then, a group-level alignment between the user preference and the item's content feature can be realized via a proposed preference aware contrastive function for enhancing cold-item recommendation. In addition, a joint objective function is introduced to achieve a better trade-off between the recommendation performance of warm items and cold items from both item-level and group-level perspectives, yielding better overall recommendation performance. Extensive experiments are conducted to demonstrate the effectiveness of the proposed method, and the results show the superiority of our method, as compared with the state-of-the-arts.

Personalized Cadence Awareness for Next Basket Recommendation

This empirical study addresses the problem of Next Basket Repurchase Recommendation (NBRR), an often overlooked aspect of Next Basket Recommendation (NBR). While NBR aims to suggest items for a user’s next basket based on their prior basket history, NBRR focuses solely on recommending items previously purchased by the user. Despite the common ground between NBR and NBRR, the latter requires a distinct approach. In this paper, we survey recent developments in the fields of NBR and NBRR, emphasizing the different strategies employed for these closely related challenges. In addition, we review the common characteristics of users’ repurchase patterns, which characterize the NBRR problem. Building on these insights, we introduce a novel hyper-convolutional model tailored to capture behavioral patterns associated with repeated purchases. To evaluate its effectiveness, we conduct experiments on three publicly available datasets, offering a comprehensive analysis across three levels of granularity: user-level, order-level, and item-level. Our analysis illuminates the conditions under which the model excels and identifies scenarios where it may encounter challenges. This research contributes valuable insights into enhancing repurchase recommendation systems and advancing the understanding of user purchase behavior in general.

Research on the Development of Digital Cultural and Creative Industry under the Background of Metaverse

The "Three Year Action Plan for the Development of Digital Economy in Jiangxi Province" clearly requires the implementation of a support plan for digital cultural and creative design projects, with a focus on supporting the development of digital cultural and creative enterprises, and building provincial-level digital cultural and creative industry demonstration bases. With the rapid development of blockchain technology and Internet applications, the digital economy has become a hot topic in today's era. Digital collectibles, as an important emerging industry in digital cultural and creative industries, are also developing rapidly. Studying the factors influencing user purchases of digital collectibles plays an important role in the industrialization and efficiency of digital cultural and creative industries. This study hopes to contribute to the realization of the vision of Digital China. This article takes the willingness of users to purchase digital collectibles in the context of the digital economy as the research object. Through a combination of online questionnaires and offline interviews, the influencing factors of Chinese netizens' willingness to purchase digital collectibles are investigated, and the contact and use of digital collectibles by Chinese residents are collected. At the same time, the collected data will be summarized, classified, and descriptive statistics will be conducted, combined with various analysis methods such as cross analysis, reliability analysis, and validity analysis. At the same time, relevant models will be established to analyze the degree of exposure and use of digital collectibles by Chinese residents, as well as the influencing factors of their selection.

Explore the Influence of E-commerce Live Broadcast on Consumers' Purchase Intention: Based on the Motivational Psychology Theory

E-commerce online live shopping has become intricately woven into the fabric of people's daily lives. This study adopts empirical statistical research methods to identify factors influencing consumers' purchase intentions within the realm of e-commerce live broadcasting. Drawing upon the Stimulus-Organism-Response (S-O-R) model and motivational psychological theory, a comprehensive model for consumer purchase intentions in the context of e-commerce live streaming is formulated. Users' perceived interactivity, perceived content quality, and perceived trust in live streamers are taken as antecedent variables, and users' emotional motivation and cognitive motivation are taken as intermediate variables. Use the user's purchase intention as the result variable. Assume that the three anthems positively affect the two intermediate variables, and the two intermediate variables positively affect the outcome variables. After a series of data analyses, all the proposed hypothesis studies are valid. In other words, the interaction of users' perception of live broadcasts when watching e-commerce, the quality of content, and their trust in live streamers will positively affect users' emotional motivation and cognitive motivation, and the emotional motivation and cognitive motivation generated by users will also positively affect users' purchase intention. There are mediating effects between affective motivation and cognitive motivation in the hypothesis model.

The Impact of Personalized New Media Advertising on Consumer Purchase Intentions: An Empirical Study Based on the Theory of Planned Behavior

This study explores the impact of personalized new media advertising on consumer purchase intentions within the framework of the Theory of Planned Behavior (TPB). Employing a survey questionnaire and comprehensive data analysis, the research quantitatively assesses the influence of personalized advertising on the TPB constructs: attitudes, subjective norms, and perceived behavioral control. These constructs are measured in terms of their effect on consumers' intentions to make a purchase. Various items can be integrated with the TPB Theory so that the personalized characteristics displayed in advertisements can be accurately grasped. After obtaining data from a random sample of 203 samples, the data from the returned questionnaires were analyzed in this study using SPSS, and the role of statistical techniques played in the analysis of the relationship between different variables. This paper is based on the results of previous studies related to personalized advertising and user purchase intention in new media. The paper also analyzes the relationship between consumer willingness to buy products and TPB in different contexts, focusing on how personalized advertising can play a role between them, whether such constructs can affect consumer willingness to buy in specific contexts, and whether they can play an effective regulatory role. This paper can make more people understand the value of personalized advertising, and the conclusions drawn can provide advice for the development of marketing work, make digital advertising strategies more effective, and play an effective role in stimulating consumers in the digital market.

Is UGC sentiment helpful for recommendation? An application of sentiment-based recommendation model

PurposeGiven the critical role of user-generated content (UGC) in e-commerce, exploring various aspects of UGC can aid in understanding user purchase intention and commodity recommendation. Therefore, this study investigates the impact of UGC on purchase decisions and proposes new recommendation models based on sentiment analysis, which are verified in Douban, one of the most popular UGC websites in China.Design/methodology/approachAfter verifying the relationship between various factors and product sales, this study proposes two models, collaborative filtering recommendation model based on sentiment (SCF) and hidden factors topics recommendation model based on sentiment (SHFT), by combining traditional collaborative filtering model (CF) and hidden factors topics model (HFT) with sentiment analysis.FindingsThe results indicate that sentiment significantly influences purchase intention. Furthermore, the proposed sentiment-based recommendation models outperform traditional CF and HFT in terms of mean absolute error (MAE) and root mean square error (RMSE). Moreover, the two models yield different outcomes for various product categories, providing actionable insights for organizers to implement more precise recommendation strategies.Practical implicationsThe findings of this study advocate the incorporation of UGC sentimental factors into websites to heighten recommendation accuracy. Additionally, different recommendation strategies can be employed for different products types.Originality/valueThis study introduces a novel perspective to the recommendation algorithm field. It not only validates the impact of UGC sentiment on purchase intention but also evaluates the proposed models with real-world data. The study provides valuable insights for managerial decision-making aimed at enhancing recommendation systems.

Strategies to mitigate the cannibalization effect between subscription video-on-demand and transactional video-on-demand

Video-on-demand (VOD) service providers face the challenge of making strategic decisions regarding the allocation of movies to specific pricing plan libraries. This study delves into the cannibalization effect that occurs when a movie transitions from the transactional video-on-demand (TVOD) library to the subscription video-on-demand (SVOD) library. We conducted a comprehensive analysis using user purchasing and viewing data for 1541 movies offered by SK Broadband, South Korea's leading VOD service provider. Our analysis employed propensity score matching and difference-in-difference methodologies. The results of our initial analysis reveal that allocating movies to SVOD leads to an 192% increase in the number of views while simultaneously 52% decreasing TVOD sales. Additionally, we investigate the characteristics of movies that are particularly effective for SVOD servicing. To accomplish this, we scrutinized 236 movies available in SK Broadband's SVOD service using a cost-effectiveness analysis. Our second analysis demonstrates that certain categories of movies, including foreign films, non-G-rated movies, animations, and films not allowed as Download-To-Own (DTO), are more suitable for allocation to SVOD libraries. Furthermore, movies with lower box office viewership numbers exhibit greater success when allocated to SVOD. This study offers insights into the strategic considerations that VOD service providers should embrace, emphasizing a content feature-driven approach to managing pricing plan combinations.

Pengaruh Influncer, Hedonic Shopping Motive, Dan Impulse Buying Terhadap Keputusan Pembelian Pada Pengguna Tiktok Shop Di Jabodetabek

This research was conducted because the researcher saw an interest in purchasing on the TikTok Shop platform. This study has a purpose to understand the influence of influencers and hedonic shopping motivation on Impulse Purchases and the influence of Impulse Buying, Influencers and Hedonic Shopping Motivation on Purchasing Decisions at Tiktok Shop in Jabodetabek. This study uses purposive sampling and probability sampling techniques by taking 170 samples of TikTok Shop user respondents in JABODETABEK. Data collection using the G-form tool with a statement questionnaire with 4 levels of linear scale. This study uses PLS-SEM techniques in hypothesis testing and data validity. The conclusion obtained from this study is that hedonic shopping motivation in TikTok Shop users and Influencers used by TikTok Shop can influence user purchases, but TikTok Shop must re-improve strategies to increase impulse purchases in its users.