Leveraging Social Media to Assist in Troubleshooting

1. A method comprising: extracting (i) user-generated information pertaining to multiple failure scenarios from at least one social media data source and (ii) one or more settings and one or more items of configuration information pertaining to each system associated with one or more of the multiple failure scenarios; determining one or more causality relationships between (i) a set of log entries associated with the multiple failure scenarios and (ii) (a) the extracted user-generated information and (b) the extracted one or more settings and one or more items of configuration information; identifying a similarity between the one or more determined causality relationships and information contained within a user query; and providing guidance to the user regarding resolving and/or obviating one or more failures associated with the user query based on said identified similarity, wherein said guidance comprises (i) multiple alerts associated with multiple failures and (ii) one or more resolutions related to the multiple alerts, (iii) a relevance score associated with each of the one or more resolutions, and wherein said providing further comprises: prioritizing said multiple alerts based on (i) a computed severity of each of the multiple failures based on (a) presence of one or more pre-determined words in the extracted user-generated information and (b) a level of expertise associated with the user that provided the extracted user-generated information, (ii) an expected lead time to failure associated with each of the multiple failures, and (iii) a computed confidence value associated with each of the one or more determined causality relationships; and computing the relevance score associated with each of one or more resolutions via Score relevance (R Di )=M relevance (Reliability Source (R Di ), Sim problem (P Di , P app ), Sim configuration (C Di , C app ), Quality(R Di )), wherein: Reliability Source (R Di ) represents reliability of the source of the respective resolution; Sim problem (P Di , P app ) represents similarity of the one or more failures associated with the user query and the failure addressed by the respective resolution; Sim configuration (C Di , C app ) represents similarity between the configuration of the system associated with the user query and the configuration of one or more systems associated with the respective resolution; and Quality(R Di ) represents a quality value associated with the respective resolution; wherein said extracting, said determining, said identifying and said providing are carried out by at least one server-side computing device.

2. The method of claim 1 , wherein said extracting comprises searching the at least one social media data source for one or more failure scenarios.

3. The method of claim 1 , wherein said at least one social media data source comprises an online discussion forum, an online message board, and/or a social network page.

4. The method of claim 1 , wherein said user-generated information comprises a user description of a failure.

5. The method of claim 1 , wherein said extracting further comprises determining resolution details associated with one or more of the multiple failure scenarios.

6. The method of claim 1 , wherein said extracting further comprises determining a severity level of one or more of the multiple failure scenarios.

7. The method of claim 1 , wherein said extracting further comprises determining a lead time associated with one or more of the multiple failure scenarios.

8. The method of claim 1 , comprising: prioritizing the one or more determined causality relationships.

9. The method of claim 1 , comprising: computing a probability of occurrence of a failure associated with the user query based on said identified similarity.

10. The method of claim 9 , wherein said providing guidance to the user comprises alerting the user about the failure associated with the user query if the computed probability of occurrence exceeds a given threshold amount.

11. The method of claim 1 , comprising: enabling receipt of feedback from the user to modify said identifying.

12. The method of claim 1 , comprising: ranking said one or more determined causality relationships.

13. The method of claim 12 , wherein said ranking comprises ranking said one or more determined causality relationships based on reliability of the at least one social media data source.

14. The method of claim 12 , wherein said ranking comprises ranking said one or more determined causality relationships based on the degree of similarity between the one or more determined causality relationships and the information contained within the user query.

15. The method of claim 12 , comprising: enabling receipt of feedback from the user to modify said ranking.

16. An article of manufacture comprising a non-transitory computer readable storage medium having computer readable instructions tangibly embodied thereon which, when implemented, cause a computer to carry out a plurality of method steps comprising: extracting (i) user-generated information pertaining to multiple failure scenarios from at least one social media data source and (ii) one or more settings and one or more items of configuration information pertaining to each system associated with one or more of the multiple failure scenarios; determining one or more causality relationships between (i) a set of log entries associated with the multiple failure scenarios and (ii) (a) the extracted user-generated information and (b) the extracted one or more settings and one or more items of configuration information; identifying a similarity between the one or more determined causality relationships and information contained within a user query; and providing guidance to the user regarding resolving and/or obviating one or more failures associated with the user query based on said identified similarity, wherein said guidance comprises (i) multiple alerts associated with multiple failures and (ii) one or more resolutions related to the multiple alerts, (iii) a relevance score associated with each of the one or more resolutions, and wherein said providing further comprises: prioritizing said multiple alerts based on (i) a computed severity of each of the multiple failures based on (a) presence of one or more pre-determined words in the extracted user-generated information and (b) a level of expertise associated with the user that provided the extracted user-generated information, (ii) an expected lead time to failure associated with each of the multiple failures, and (iii) a computed confidence value associated with each of the one or more determined causality relationships; and computing the relevance score associated with each of one or more resolutions via Score relevance (R Di )=M relevance (Reliability Source (R Di ), Sim problem (P Di , P app ), Sim configuration (C Di , C app ), Quality(R Di )), wherein: Reliability Source (R Di ) represents reliability of the source of the respective resolution: Sim problem (P Di , P app ) represents similarity of the one or more failures associated with the user query and the failure addressed by the respective resolution; Sim configuration (C Di , C app ) represents similarity between the configuration of the system associated with the user query and the configuration of one or more systems associated with the respective resolution; and Quality(R Di ) represents a quality value associated with the respective resolution.

17. A system comprising: a memory; and at least one processor coupled to the memory and configured for: extracting (i) user-generated information pertaining to multiple failure scenarios from at least one social media data source and (ii) one or more settings and one or more items of configuration information pertaining to each system associated with one or more of the multiple failure scenarios; determining one or more causality relationships between (i) a set of log entries associated with the multiple failure scenarios and (ii) (a) the extracted user-generated information and (b) the extracted one or more settings and one or more items of configuration information; identifying a similarity between the one or more determined causality relationships and information contained within a user query; and providing guidance to the user regarding resolving and/or obviating one or more failures associated with the user query based on said identified similarity, wherein said guidance comprises (i) multiple alerts associated with multiple failures and (ii) one or more resolutions related to the multiple alerts, (iii) a relevance score associated with each of the one or more resolutions, and wherein said providing further comprises: prioritizing said multiple alerts based on (i) a computed severity of each of the multiple failures based on (a) presence of one or more pre-determined words in the extracted user-generated information and (b) a level of expertise associated with the user that provided the extracted user-generated information, (ii) an expected lead time to failure associated with each of the multiple failures, and (iii) a computed confidence value associated with each of the one or more determined causality relationships; and computing the relevance score associated with each of one or more resolutions via Score relevance (R Di )=M relevance (Reliability Source (R Di ), Sim problem (P Di , P app ), Sim configuration (C Di , C app ), Quality(R Di )), wherein: Reliability Source (R Di ) represents reliability of the source of the respective resolution; Sim problem (P Di , P app ) represents similarity of the one or more failures associated with the user query and the failure addressed by the respective resolution; Sim configuration (C Di , C app ) represents similarity between the configuration of the system associated with the user query and the configuration of one or more systems associated with the respective resolution; and Quality(R Di ) represents a quality value associated with the respective resolution.

18. The method of claim 1 , wherein said computed confidence value is based on authenticity of the at least one social media data source, popularity of the at least one social media data source, and/or an amount of additional user-generated information related to the extracted user-generated information.