MLManman Luo

Manman Luo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Manman Luo has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    New Ontology-Based Model for Sentiment Aspect Detection

    by Manman Luo, Xiangming Mu

    Sentiment aspect detection aims to identify the presence of sentiments towards specific aspects of an entity, such as a product, restaurant, or policy. Sentiment aspect detection plays a crucial role in aspect-based entity sentiment analysis. A typical approach for detecting sentiment aspects involves applying machine learning techniques to train a model based on human-annotated data. Although machine learning-based models have achieved significant progress, these models often act as a “black box” and lack transparency in their reasoning processes. It is unclear what factors contribute to the models’ effectiveness in detecting sentiment aspects. To address the issue of intransparency in machine learning-based sentiment aspect detection models, this study aims to investigate the effectiveness of ontology-based models for sentiment aspect detection in restaurant reviews. The model was developed based on ontology terms related to six key restaurant aspects: food, service, ambience, cleanliness, location, and price, using 6,000 annotated Yelp reviews. Different ontology model construction strategies, including the source of ontology terms and part-of-speech (POS) tags, were explored. The ontology-based models were evaluated based on performance improvement over a baseline model for accurately detecting sentiments associated with sentiment aspects. The results showed the effectiveness of the ontology model as compared to the baseline model across all restaurant aspects except food: service (21.81%), price (12.95%), cleanliness (9.49%), ambience (7.81%), and location (3.69%). These findings help to understand the impact of an ontology model on sentiment aspect detection and provide an ontology-based approach for more interpretable sentiment aspect detection models.

  • Design Matters in Web Credibility Assessment: Interactive Design as a Social Validation Tool for Online Health Information Seekers

    by Wonchan Choi, Sang-Yeon Kim, Manman Luo

    This study explored what makes users perceive a website as a credible source of health information and how web credibility assessment, in turn, influences their health information-seeking behaviors. Exploratory factor analysis was conducted with survey responses from college students (NN = 141) who assessed credibility markers of a website they normally visit to address health concerns. A 4-factor solution emerged as the best summary of the data: (a) content, (b) interaction design, (c) information design, and (d) source. Identified components were used in a linear model to explore the effects of different web credibility types on perceptual, attitudinal, and behavioral outcomes. Alongside content-related attributes (e.g., recency of the information), interaction design-related elements (e.g., ability to interact with other users) were significantly associated with most dependent variables examined in the study (e.g., trust in the information on the site, willingness to follow the advice, and willingness to recommend the site to others). Current results imply that users count on not only content-related cues or heuristics, but also interactive design features as helpful tools for mobilizing social resources (e.g., fellow users) to validate online health information. Theoretical and practical implications of the study findings and future research directions are discussed.


  • Open Access

    Identifying factors impacting entity sentiment analysis: A case study of sentiment analysis in the context of news reports

    by Manman Luo, Xiangming Mu

    Entity sentiment analysis aims to analyze sentiment for a specific entity. As entity sentiment analysis requires the understanding of entities and associated entities, this paper presents preliminary findings from an exploratory analysis of factors affecting entity sentiment analysis in the news report context using a data set of 8,754 paragraphs. An entity coding schema was developed based on grounded theory. The coding result shows that 29% of paragraphs express sentiment directly, and 24% express indirectly. Negative biased entities (towards target entity) may significantly affect the accuracy of entity sentiment analysis. The findings may shed light on future exploration in improving the accuracy of entity sentiment analysis.