Résultats de recherche pour « Brand-Topic Model »

Monitoring online customer reviews is important for business organisations to measure customer satisfaction and better manage their reputations. In this paper, we propose a novel dynamic Brand-Topic Model (dBTM) which is able to automatically detect and track brand-associated sentiment scores and polarity-bearing topics from product reviews organised in temporally-ordered time intervals. dBTM models the evolution of the latent brand polarity scores and the topic-word distributions over time by Gaussian state space models. It also incorporates a meta learning strategy to control the update of the topic-word distribution in each time interval in order to ensure smooth topic transitions and better brand score predictions. It has been evaluated on a dataset constructed from MakeupAlley reviews and a hotel review dataset. Experimental results show that dBTM outperforms a number of competitive baselines in brand ranking, achieving a good balance of topic coherence and uniqueness, and extracting well-separated polarity-bearing topics across time intervals.

This article highlights how social media data and language analysis can help managers understand brand positioning and brand competitive spaces to enable them to make various strategic and tactical decisions about brands. The authors use the output of topic models at the brand level to evaluate similarities between brands and to identify potential cobrand partners. In addition to using average topic probabilities to assess brands’ relationships to each other, they incorporate a differential language analysis framework, which implements scientific inference with multi-test-corrected hypothesis testing, to evaluate positive and negative topic correlates of brand names. The authors highlight the various applications of these approaches in decision making for brand management, including the assessment of brand positioning and future cobranding partnerships, design of marketing communication, identification of new product introductions, and identification of potential negative brand associations that can pose a threat to a brand's image. Moreover, they introduce a new metric, “temporal topic variability,” that can serve as an early warning of future changes in consumer preference. The authors evaluate social media analytic contributions against offline survey data. They demonstrate their approach with a sample of 193 brands, representing a broad set of categories, and discuss its implications.

Multi-brand analysis based on review comments and ratings is a commonly used strategy to compare different brands in marketing. It can help consumers make more informed decisions and help marketers understand their brand's position in the market. In this work, we propose a multifacet hierarchical sentiment-topic model (MH-STM) to detect brand-associated sentiment polarities towards multiple comparative aspects from online customer reviews. The proposed method is built on a unified generative framework that explains review words with a hierarchical brand-associated topic model and the overall polarity score with a regression model on the empirical topic distribution. Moreover, a novel hierarchical Polya urn (HPU) scheme is proposed to enhance the topic-word association among topic hierarchy, such that the general topics shared by all brands are separated effectively from the unique topics specific to individual brands. The performance of the proposed method is evaluated on both synthetic data and two real-world review corpora. Experimental studies demonstrate that the proposed method can be effective in detecting reasonable topic hierarchy and deriving accurate brand-associated rankings on multi-aspects.

Topic Modeling is a well-known unsupervised learning technique used when dealing with text data. It is used to discover latent patterns, called topics, in a collection of documents (corpus). This technique provides a convenient way to retrieve information from unclassified and unstructured text. Topic Modeling tasks have been performed for tracking events/topics/trends in different domains such as academic, public health, marketing, news, and so on. In this paper, we propose a framework for extracting topics from a large dataset of short messages, for brand interest tracking purposes. The framework consists training LDA topic models for each brand using time intervals, and then applying the model on aggregated documents. Additionally, we present a set of preprocessing tasks that helped to improve the topic models and the corresponding outputs. The experiments demonstrate that topic modeling can successfully track people’s discussions on Social Networks even in massive datasets, and ca pture those topics spiked by real-life events.

In this paper, we propose the Brand-Topic Model (BTM) which aims to detect brand-associated polarity-bearing topics from product reviews. Different from existing models for sentiment-topic extraction which assume topics are grouped under discrete sentiment categories such as `positive', `negative' and `neural', BTM is able to automatically infer real-valued brand-associated sentiment scores and generate fine-grained sentiment-topics in which we can observe continuous changes of words under a certain topic (e.g., `shaver' or `cream') while its associated sentiment gradually varies from negative to positive. BTM is built on the Poisson factorisation model with the incorporation of adversarial learning. It has been evaluated on a dataset constructed from Amazon reviews. Experimental results show that BTM outperforms a number of competitive baselines in brand ranking, achieving a better balance of topic coherence and uniqueness, and extracting better-separated polarity-bearing topics.

In survival analysis, traditional models assume all individuals will eventually experience the event of interest. However, advances in therapeutics have led to multiple clinical contexts with potentially curative therapies, and in these contexts, certain individuals may never experience the event. Statisticians have developed cure models as a methodology to address this challenge. Nonetheless, despite significant statistical advances in cure models, we have seen more limited uptake in biomedical applications, and we hypothesize that this is caused by limited guidance in the appropriate application of cure models. Cure models require specific identifiability conditions for valid parameter estimation, and previous reports have demonstrated significant issues with the inappropriate application of cure models. Existing tutorials for cure models focus on model implementation and either assume or provide only limited guidance on whether cure modeling is appropriate for the given dataset. This tutorial addresses this gap by describing a systematic procedure that integrates clinical judgment, visual inspection of Kaplan-Meier curves, and quantitative evaluation. We provide a worked example using data from a randomized clinical trial in acute myeloid leukemia, and we also summarize findings from a series of other datasets of hematopoietic cell transplantation to suggest broad practical guidance for choosing to apply cure models. By systematically evaluating cure model appropriateness before fitting these models, researchers can achieve more reliable survival analysis and improved clinical decision-making.

Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and execution feedback. We introduce MachEmbodied-VLM (ME-VLM), a unified vision-language model with two variants, 4B and 35B-A3B, that brings together embodied cognition and multimodal agent capabilities. Our work emphasizes physical perception and spatiotemporal reasoning, together with planning, interaction, and outcome assessment in both digital and physical environments. We construct training data spanning embodied and multimodal agent tasks, including execution observations and feedback to support outcome assessment and decision refinement. The training pipeline comprises embodied capability injection, separate reinforcement learning of embodied and multimodal-agent experts, and multi-teacher on-policy distillation that consolidates their complementary capabilities into a single model. Experiments show competitive performance on both embodied and agent benchmarks, as well as on autonomous-driving and embodied-navigation tasks. For edge deployment, visual token compression, W4A8 quantization, and hardware-software co-optimization enable on-device inference of the 4B variant on the M100, reducing prefill latency from 400 ms to 188 ms. Project Page: https://machembodied.com/ME-Brain/ME-VLM.html Code Repository: https://github.com/MachEmbodied/ME-VLM

Manuscript type: Empirical paper Research Aims: This paper aims to identify the topics of social media posts (on Twitter) from local skincare brands in Indonesia. Design/methodology/approach: This descriptive study applied text analysis methods, specifically frequency analysis and topic modeling with the Latent Dirichlet Allocation (LDA) method. Data were collected from the top four skincare brands with over 10,000 followers using Twitter Academic API interfaced through the Twarc package in Python. The dataset contained 1290 tweets from Wardah, 17,491 tweets from Avoskin, 1,968 tweets from Somethinc, and 590 tweets from Whitelab. The data analysis used quanteda and topicmodels packages from R software. Research findings: The findings revealed that the brands’ tweets can be categorised into 8-10 topics, which can be distilled further into three significant functions proposed by Saxton and Waters (2014): information, promotion and mobilisation, and community building and dialogue. Theoretical Contribution/Originality: This study adds to the body of knowledge regarding social media marketing by adding insights into how local Indonesian brands carry out their social media marketing efforts. Practitioner/Policy Implication: The findings implied that marketing managers should emphasise providing timely and relevant information as a base that can be used to build dialogic communication efforts with their audience. Research limitation/Implications: This study only looked at four brands in the local skincare product category. In addition, this study applied automated topic modeling with LDA, which needed an a priori number of topics, which might affect the topic labelling. Furthermore, this study’s scope was limited to categorising the brand posts without examining the effects of brand post types on engagement metrics. Future studies can examine more samples by observing other product categories, applying thematic analysis to code each tweet, and comparing the results to topic modeling results. Lastly, future studies can examine the relationship between brand post types/categories and engagement metrics such as likes, comments, and retweets. Keywords: Cosmetics Brands, Social Media Marketing, Skincare, Topic Modeling, Twitter