Recommender System based on Extracted Data from Different Social Media. A Study of Twitter and LinkedIn
Bibliographic record
Abstract
The number of social media users and the amount of available digital information on them is growing exponentially. This explosive rise in the accessible data on social media may cause confusion for users and leads to unpleasant experience since the overwhelming number of various choices makes finding the items of interest too difficult. As an effective solution, recommender systems are used to predict user's responses to existing options. Each social media site attempts to develop recommending algorithms as efficiently as possible based on the users' contributions. In addition, many studies have investigated various recommending and predicting approaches for a specific application. However, considering the relationships between different data provided by people on different social media sites and using them to produce new recommender systems were the subject of only a few studies. To fill this gap, the objective of this study is developing recommender systems which are connecting two social media together. We collected data from Twitter and LinkedIn accounts of some computer scientists and developed new recommender systems: a collaborative, a content-based and two hybrids, which relate computer scientists' skills, declared on their LinkedIn profile, to their Twitter's followings. Using this data, we can generate useful recommendations not possible within just one social site. We recommend new Twitter accounts to computer scientists based on their skills and interests; and also predict their skills based on the accounts they are following on Twitter. The precision and usefulness of these recommender and predicator algorithms are investigated using a real dataset of Twitter and LinkedIn profiles; then their performances are compared to each other in terms of accuracy and time consumption.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".