Online Reputation Monitoring Research Articles

Exploring an In-house Online Reputation Monitoring Implementation

Today, our online reputation can be developed through subjective opinions communication by netizen on social media. Online reputation especially for business entities can affect in many aspects such as sales and customer loyalty. Due to high amount of social data (e.g. comments), the manual approach in monitoring subjective opinions towards our brands, products or name is no longer relevant. Therefore, entities either organizations or individuals should monitor their online reputation using social media analytics tools such as sentiment analysis to mitigate reputation attack. However, Online Reputation Monitoring (ORMo) is yet a common practice where most practitioners are large corporations. Outsourcing is a good option but entities must allocate some costs which a burden for most small and medium entities. Thus, implementing social media analytics in-house ORMo by entities is a reasonable option. However, the guideline to implement in-house ORMo is still not well explored including what are the needed features in an ORMo tool. Therefore, this research attempts to explore on how to implement an in-house ORMo at affordable cost but reliable. In achieving the objective, this research involved four stages of investigations which are needs assessment of ORMo tool features, prototype development, simulation and expert survey for validation. This research found that in-house ORMo can be implemented at minimal cost using existing resources and the accuracy can be improved by updating the collection of words with its sentiment polarity. The results of this research can be the basis for an in-house ORMo tool implementation and for reviewing the existing ORMo tool.

Automatic generation of entity-oriented summaries for reputation management

Producing online reputation summaries for an entity (company, brand, etc.) is a focused summarization task with a distinctive feature: issues that may affect the reputation of the entity take priority in the summary. In this paper we (i) present a new test collection of manually created (abstractive and extractive) reputation reports which summarize tweet streams for 31 companies in the banking and automobile domains; (ii) propose a novel methodology to evaluate summaries in the context of online reputation monitoring, which profits from an analogy between reputation reports and the problem of diversity in search; and (iii) provide empirical evidence that producing reputation reports is different from a standard summarization problem, and incorporating priority signals is essential to address the task effectively.

Initiating an Online Reputation Monitoring System with Open Source Analytics Tools

Online reputation is an invaluable asset for modern organizations as it can help in business performance especially in sales and profit. However, if we are not aware of our reputation, it is difficult to maintain it. Thus, social media analytics is a new tool that can provide online reputation monitoring in various ways such as sentiment analysis. As a result, numerous large-scale organizations have implemented Online Reputation Monitoring (ORM) systems. However, this solution is not supposed to be exclusively for high-income organizations, as many organizations regardless sizes and types are now online. This research attempts to propose an affordable and reliable ORM system using combination of open source analytics tools for both novice practitioners and academicians. We also evaluate its prediction accuracy and we discovered that the system provides acceptable predictions (sixty percent accuracy) and demonstrate a tally prediction of major polarity by human annotation. The proposed system can help in supporting business decisions with flexible monitoring strategies especially for organization that want to initiate and administrate ORM themselves at low cost.

TexRep: A Text Mining Framework for Online Reputation Monitoring

This work aims to understand, formalize and explore the scientific challenges of using unstructured text data from different Web sources for Online Reputation Monitoring. We here present TexRep, an adaptable text mining framework specifically tailored for Online Reputation Monitoring that can be reused in multiple application scenarios, from politics to finance. This framework is able to collect texts from online media, such as Twitter, and identify entities of interest and classify sentiment polarity and intensity. The framework supports multiple data aggregation methods, as well as visualization and modeling techniques that can be used for both descriptive analytics, such as analyze how political polls evolve over time, and predictive analytics, such as predict elections. We here present case studies that illustrate and validate TexRep for Online Reputation Monitoring. In particular, we provide an evaluation of TexRep Entity Filtering and Sentiment Analysis modules using well known external benchmarks. We also present an illustrative example of TexRep application in the political domain.

Online Reputation Monitoring: An Exploratory Study on Italian Hotel Managers’ Practices

ABSTRACTThis study aims to understand current Italian hotel managers’ practices in monitoring online reviews included on travel websites and online travel agencies. Results obtained by a web survey indicate what hotel managers monitor (rating, rankings, guest comments regarding different service elements) and managers’ orientation in replying to customer reviews. Findings may support online reputation management tools providers and consulting firms by highlighting the degree of hoteliers’ interest in UGC monitoring and providing insights on possible factors that differentiate current management practices and should be considered in order to offer technical solutions coherent with the distinctiveness of Italian context.