Social Media Recommendation Research Articles

Understanding News 2.0: A framework for explaining the number of comments from readers on online news

In the era of News 2.0, the number of comments can indicate the influence of online news, which brings potential social value and economic benefits. The present study proposes a framework that involves integrating the features of news structure, news content, and reader usage (social media recommendation) to explain the number of comments. The results of logistic regression suggest that the proposed framework is a powerful tool for explaining the number of comments (R2=47.1%). The relative and mediating role of recommendation in social media from readers is also explored. The theoretical and managerial implications of these results are provided.

Therapeutic affordances of social media: emergent themes from a global online survey of people with chronic pain.

BackgroundResearch continues to present tenuous suggestions that social media is well suited to enhance management of chronic disease and improve health outcomes. Various studies have presented qualitative reports of health outcomes from social media use and have examined discourse and communication themes occurring through different social media. However, there is an absence of published studies examining and unpacking the underlying therapeutic mechanisms driving social media’s effects.ObjectiveThis paper presents a qualitative analysis thoroughly describing what social media therapeutically affords people living with chronic pain who are self-managing their condition. From this therapeutic affordance perspective, we aim to formulate a preliminary conceptual model aimed at better understanding "how" social media can influence patient outcomes.MethodsIn total, 218 people with chronic pain (PWCP) completed an online survey, investigating patient-reported outcomes (PROs) from social media use. Supplementary to quantitative data collected, participants were also given the opportunity to provide further open commentary regarding their use of social media as part of chronic pain management; 68/218 unique users (31.2%) chose to provide these free-text responses. Through thematic content analysis, 117 free-text responses regarding 10 types of social media were coded. Quotes were extracted and tabulated based on therapeutic affordances that we had previously identified. Inductive analysis was then performed to code defining language and emergent themes central to describing each affordance. Three investigators examined the responses, developed the coding scheme, and applied the coding to the data.ResultsWe extracted 155 quotes from 117 free-text responses. The largest source of quotes came from social network site users (78/155, 50.3%). Analysis of component language used to describe the aforementioned affordances and emergent themes resulted in a final revision and renaming of therapeutic affordances: "exploration" (52/155, 33.5% of quotes), "connection" (50/155, 32.3% of quotes), "narration" (33/155, 21.3% of quotes), "adaptation" (13/155, 8.4% of quotes), and "self-presentation" (7/155, 4.5% of quotes). Of the most described affordances, "exploration" was based on a propensity for participants to explain their social media use for information seeking purposes. "Connection" placed greater emphasis on interaction, highlighting themes of "exchanging information" and "mitigating isolation". Responses regarding "narration" highlighted the value of shared experiences and the emotionally cathartic role this plays.ConclusionsMuch of the efficacy of social media may be explicable via a closer examination of therapeutic affordances. Particular areas that warrant attention include social media’s ability to filter and guide people to useful information, connect individuals, and share experiences. Further research into a variety of chronic conditions is warranted. Coupled with the results of the present study, a greater theoretical basis detailing how social media may foster health outcomes may lead to an improved evidence base for conducting research and may inform recommendations for social media use in chronic disease management.

Persuasive messages, popularity cohesion, and message diffusion in social media marketing

Social media marketing is an influential marketing method. Liking or sharing social media messages can increase the effects of popular cohesion and message diffusion. This research investigates how persuasive messages (i.e., argument quality, post popularity, and post attractiveness) can lead internet users to click like and share messages in social media marketing activities. This research develops hypotheses on the basis of elaboration likelihood model and a 392 fans survey from a fan page on Facebook. Structural equation modeling analyzes questionnaire data. Results show that the three types of persuasive messages are important to click like and to share post messages. Post popularity is essential and works through both central route and peripheral according to research model. In addition, different message characteristics and user groups have different communicating behaviors. This research provides valuable recommendations for social media marketing activities.

Mining affective text to improve social media item recommendation

Social media websites, such as YouTube and Flicker, are currently gaining in popularity. A large volume of information is generated by online users and how to appropriately provide personalized content is becoming more challenging. Traditional recommendation models are overly dependent on preference ratings and often suffer from the problem of “data sparsity”. Recent research has attempted to integrate sentiment analysis results of online affective texts into recommendation models; however, these studies are still limited. The one class collaborative filtering (OCCF) method is more applicable in the social media scenario yet it is insufficient for item recommendation. In this study, we develop a novel sentiment-aware social media recommendation framework, referred to as SA_OCCF, in order to tackle the above challenges. We leverage inferred sentiment feedback information and OCCF models to improve recommendation performance. We conduct comprehensive experiments on a real social media web site to verify the effectiveness of the proposed framework and methods. The results show that the proposed methods are effective in improving the performance of the baseline OCCF methods.

Cold-Start Recommendation Using Bi-Clustering and Fusion for Large-Scale Social Recommender Systems

Social recommender systems leverage collaborative filtering (CF) to serve users with content that is of potential interesting to active users. A wide spectrum of CF schemes has been proposed. However, most of them cannot deal with the cold-start problem that denotes a situation that social media sites fail to draw recommendation for new items, users or both. In addition, they regard that all ratings equally contribute to the social media recommendation. This supposition is against the fact that low-level ratings contribute little to suggesting items that are likely to be of interest of users. To this end, we propose bi-clustering and fusion (BiFu)-a newly-fashioned scheme for the cold-start problem based on the BiFu techniques under a cloud computing setting. To identify the rating sources for recommendation, it introduces the concepts of popular items and frequent raters. To reduce the dimensionality of the rating matrix, BiFu leverages the bi-clustering technique. To overcome the data sparsity and rating diversity, it employs the smoothing and fusion technique. Finally, BiFu recommends social media contents from both item and user clusters. Experimental results show that BiFu significantly alleviates the cold-start problem in terms of accuracy and scalability.

Using RSSI Simple Localization Method to Implement the Context-Aware and Social Recommendation System

This study integrates the concept of context-awareness with association algorithms and social media to establish the Context-aware and Social Recommendation System (CASRS). The Simple RSSI Indoor Localization Module (SRILM) locates the user position; integrating SRILM with Apriori Recommendation Module (ARM) provides effective recommended product information. The Social Media Recommendation Module (SMRM) connects to users social relations, so that the effectiveness for users to gain product information is greatly enhanced. This study develops the system based on actual context.

Impact and degree of user sociability in social media

Users’ posts receive feedback from other users in the form of comments, trackback, or recommendation in social media. These interactions form a graph in which the vertices represent a set of users, while the edges represent a set of feedback. Thus, the problem of users’ rankings can be approached in terms of the link analysis of the social interactions between the users themselves within this graph. Link analysis algorithms, such as PageRank and HITS, have often been applied for users’ rankings, especially for users’ reputation, but no consideration has been given to how the user’s sociability can affect the user’s reputation. We propose two factors that affect the score of every user, the user’s reputation, and the user’s sociability, to address this problem. We present novel schemes that can effectively and separately estimate the reputation and sociability of the users. Furthermore, we present schemes to measure the degree of the user’s sociability in a social network. Our experiments show that: (1) our schemes can effectively separate the user’s pure reputation from the user’s sociability (2) the pure reputation is capable of producing superior user ranking results than can previous work (3) the degree of user sociability for each social network varies and reveals significant characteristics of the corresponding network.

User comments for news recommendation in forum-based social media

News recommendation and user interaction are important features in many Web-based news services. The former helps users identify the most relevant news for further information. The latter enables collaborated information sharing among users with their comments following news postings. This research is intended to marry these two features together for an adaptive recommender system that utilizes reader comments to refine the recommendation of news in accordance with the evolving topic. This then turns the traditional “push-data” type of news recommendation to “discussion” moderator that can intelligently assist online forums. In addition, to alleviate the problem of recommending essentially identical articles, the relationship (duplicate, generalization, or specialization) between recommended news articles and the original posting is investigated. Our experiments indicate that our proposed solutions provide an improved news recommendation service in forum-based social media.

News Recommendation in Forum-Based Social Media

Self-publication of news on Web sites is becoming a common application platform to enable more engaging interaction among users. Discussion in the form of comments following news postings can be effectively facilitated if the service provider can recommend articles based on not only the original news itself but also the thread of changing comments. This turns the traditional news recommendation to a "discussion moderator" that can intelligently assist online forums. In this work, we present a framework to implement such adaptive news recommendation. In addition, to alleviate the problem of recommending essentially identical articles, the relationship (duplication, generalization or specialization) between suggested news articles and the original posting is investigated. Experiments indicate that our proposed solutions provide an enhanced news recommendation service in forum-based social media.